commit 3bfcb71de732acee2287c84e766f27fe752df372 Author: ModelHub XC Date: Mon Aug 24 14:39:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: DavidAU/ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1074d9 --- /dev/null +++ b/README.md @@ -0,0 +1,132 @@ +--- +license: apache-2.0 +datasets: +- TeichAI/claude-4.5-opus-high-reasoning-250x +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- mixture of experts +- moe +- 64 experts +- uncensored +- unsloth +- finetune +- All use cases +- bfloat16 +- creative +- creative writing +- fiction writing +- plot generation +- sub-plot generation +- fiction writing +- story generation +- scene continue +- storytelling +- fiction story +- science fiction +- romance +- all genres +- story +- writing +- vivid prosing +- vivid writing +- fiction +base_model: +- baidu/ERNIE-4.5-21B-A3B-Thinking +--- + +

ERNIE-21B-A3B-Claude-4.5-High-OPUS-Thinking

+ +This is a uncensored, full deep thinking Ernie 21B-A3B (MOE, 64 experts) fine tune using Claude 4.5 High Opus +reasoning dataset via Unsloth via local hardware, Linux (for windows). + +Note this model is mostly uncensored right from the "factory" so to speak. + +Model excels in creative (brainstorming, creative prose) as well as general usage. + +Reasoning is compact, but detailed (very detailed) and right to the "point" so to speak. + +CRITICAL SETTINGS: +- for creative suggest rep pen of 1.01 to 1.1 +- for general work rep pen of 1 (off), 1.05 or 1.1 +- Lower quants MAY LOOP in some cases. + +Reasoning affects: +- General model operation. +- Output generation +- Benchmarks. + +Model Features: +- 128k context +- Temp range .1 to 2.5. +- Reasoning is temp stable. + +You may want to visit Baidu's repo for this model for root/core benchmarks and settings. + +https://huggingface.co/baidu/ERNIE-4.5-21B-A3B-Thinking + +Enjoy the freedom! + +BENCHMARKS: + +``` +arc_challenge,arc_easy,boolq,hellaswag,openbookqa,piqa, winogrande + +0.392 ,0.489 ,0.631,0.686 ,0.364 ,0.771 ,0.631 +``` + +VS (regular model): + +``` +0.331 ,0.440 ,0.628,0.663 ,0.338 ,0.725 ,0.567 +``` + +--- + +SPECIAL THANKS TO: +- Team "TeichAI" for the excellent dataset. +- Team "Unsloth" for making the training painless. +- Team "Nightmedia" for Benchmarks and co-labing. + +--- + +Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model: + +In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ; + +Set the "Smoothing_factor" to 1.5 + +: in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F" + +: in text-generation-webui -> parameters -> lower right. + +: In Silly Tavern this is called: "Smoothing" + + +NOTE: For "text-generation-webui" + +-> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model) + +Source versions (and config files) of my models are here: + +https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be + +OTHER OPTIONS: + +- Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor") + +- If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted. + +Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers + +This a "Class 1" model: + +For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see: + +[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] + +You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here: + +[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..df99882 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,102 @@ +{{- '<|im_start|>system +' }}{%- if messages[0].role != 'system' and not system_settings %}{{- ' +think_mode=True +' }}{%- else%}{{- ' +' }}{{- system_settings + ' +' if system_settings else '' }}{{- (messages[0].content + ' +' if messages[0].role == 'system' else '') + ' + + +think_mode=True +' }}{%- endif %}{%- if tools %}{{- " + +" }}{{- ' +' }}{{-'['}}{% for tool in tools %}{{'{"type": "function", "function": '}}{{-(tool.function | tojson)}}}{%-if not loop.last%},{%- endif %}{%endfor%}{{-']'}}{{- " +" }}{%- endif %}{{-'<|im_end|> + +' }}{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + ' +' + content + '<|im_end|>' + ' + +' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.thoughts is string %} + {%- set reasoning_content = message.thoughts %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip(' +').split('')[-1].lstrip(' +') %} + {%- set content = content.split('')[-1].lstrip(' +') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index and (loop.last or (not loop.last and reasoning_content)) %} {{- '<|im_start|>' + message.role + ' + +' + reasoning_content.strip(' +') + ' + +' }} {%- else %} {{- '<|im_start|>' + message.role + ' +' }} {%- endif %} {%- if content|length > 0 %} {{- ' +' + content + ' + +' }} {%- endif %} {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- ' +' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- ' + +{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '} + +' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|> + +' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>tool' }} + {%- endif %} + {{- ' +' }} + {{- message.content|tojson }} + {{- '' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|> + +' }} + {%- endif %} + {%- endif %} +{%- endfor %} + {%- if add_generation_prompt is defined and add_generation_prompt %}{{- "<|im_start|>assistant + +"}}{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..07f20be --- /dev/null +++ b/config.json @@ -0,0 +1,44 @@ +{ + "architectures": [ + "Ernie4_5_MoeForCausalLM" + ], + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 131072, + "model_type": "ernie4_5_moe", + "moe_capacity": [ + 64, + 64, + 64 + ], + "moe_gate": "top2_fused", + "moe_intermediate_size": 1536, + "moe_k": 6, + "moe_layer_end_index": 27, + "moe_layer_interval": 1, + "moe_layer_start_index": 1, + "moe_norm_min": 1e-12, + "moe_num_experts": 64, + "moe_num_shared_experts": 2, + "moe_use_aux_free": true, + "num_attention_heads": 20, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "output_router_logits": false, + "pad_token_id": 0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 500000, + "tie_word_embeddings": true, + "router_aux_loss_coef": 0.001, + "transformers_version": "4.57.6", + "unsloth_fixed": true, + "use_bias": false, + "use_cache": true, + "vocab_size": 103424 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bbdefab --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.57.6" +} diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..055e269 --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cdfe56a9028a879fbbdb0d1f1d4db95c670fcf1e217121d0164b02c1ed48ff9 +size 4998530656 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..ef06856 --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e3bec67615314ba0c98f43eda9aacbd6ff4e2aa743e6f740d3b9686cb0f618 +size 4995919560 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..09b18d5 --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82b34e1d1504fa30fa9aa7dbb588131d037c14cb51c92e9751800ce9c35f9a6f +size 4995919560 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..78e1ba6 --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04534be3145b188fdb82f92c66812455cb97b595a7919982b3f534cf78f827e +size 4996586088 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..bb212c0 --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f805598a3f454775ccb2041d77a044f4ca2ceae27189e120c8d096c4b104339 +size 4995920184 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..938691e --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5107640cc55dddfc23eb27070773bf76eefe76edcc90777ea70d7e78ab510a7 +size 4995920192 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..9f66d2a --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5007595a7e7ad2dbe1e9b1a546983708f4d5a34787ef1e0ea4ea51a46fd742c +size 4995920192 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..d7ecee9 --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0209030895bff99fdd00b569764dbd712e11365fecd59829073bcb9ec324b7de +size 4995920200 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..664345e --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4905217ce384846bcd27b8687ffd80f42a12fe134f0bcccef88032d66a64af32 +size 3689771704 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d499c94 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,5500 @@ +{ + "metadata": { + "total_parameters": 21825437888, + "total_size": 43659726592 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.gate.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.moe_statics.e_score_correction_bias": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.gate.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.moe_statics.e_score_correction_bias": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.gate.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.moe_statics.e_score_correction_bias": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.gate.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.moe_statics.e_score_correction_bias": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.gate.weight": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.moe_statics.e_score_correction_bias": "model-00004-of-00009.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.gate.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.moe_statics.e_score_correction_bias": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.gate.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.moe_statics.e_score_correction_bias": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.gate.weight": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.moe_statics.e_score_correction_bias": "model-00005-of-00009.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.gate.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.moe_statics.e_score_correction_bias": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.gate.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.moe_statics.e_score_correction_bias": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.gate.weight": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.moe_statics.e_score_correction_bias": "model-00006-of-00009.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.gate.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.moe_statics.e_score_correction_bias": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.gate.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.moe_statics.e_score_correction_bias": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.gate.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.moe_statics.e_score_correction_bias": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.gate.weight": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.moe_statics.e_score_correction_bias": "model-00007-of-00009.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.gate.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.moe_statics.e_score_correction_bias": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.gate.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.moe_statics.e_score_correction_bias": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.gate.weight": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.moe_statics.e_score_correction_bias": "model-00008-of-00009.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.gate.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.moe_statics.e_score_correction_bias": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.gate.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.moe_statics.e_score_correction_bias": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.gate.weight": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.moe_statics.e_score_correction_bias": "model-00001-of-00009.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.gate.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.moe_statics.e_score_correction_bias": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.gate.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.moe_statics.e_score_correction_bias": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.gate.weight": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.moe_statics.e_score_correction_bias": "model-00002-of-00009.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.gate.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.moe_statics.e_score_correction_bias": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.gate.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.moe_statics.e_score_correction_bias": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.gate.weight": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.moe_statics.e_score_correction_bias": "model-00003-of-00009.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.norm.weight": "model-00009-of-00009.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..74071a0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,51 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "cls_token": { + "content": "<|begin_of_sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "mask_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "sep_token": { + "content": "<|end_of_sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..9407f1e --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c25a6ebd867c54435ca2fdb8fdd3187699aea9bd85d83b6d43f50ebedb4564 +size 10999540 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..b4d38b5 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098d756440604e3829c6c2375f835a82a1968c044b74e561f4b0084e53befd2e +size 1614702 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..44fcb69 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,282 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "0", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "4": { + "content": "1", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "2", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "3", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "4", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "5", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "6", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "7", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "8", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "9", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100272": { + "content": "<|end_of_sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100273": { + "content": "<|begin_of_sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100274": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100281": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "100282": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100295": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100296": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100297": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100298": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100299": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100300": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100301": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100302": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100303": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100304": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100305": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100306": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100307": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100308": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "cls_token": "<|begin_of_sentence|>", + "eos_token": "", + "extra_special_tokens": {}, + "header_end_token": "", + "header_start_token": "", + "legacy": true, + "mask_token": "", + "model_max_length": 131072, + "pad_token": "", + "padding_side": "left", + "sep_token": "<|end_of_sentence|>", + "sys_end_token": "", + "sys_start_token": "", + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}