From 119ce3a14ac824921ec899141848a654a3d627a3 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 9 Aug 2026 13:37:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-fp16 Source: Original Platform --- ._README.md | Bin 0 -> 4096 bytes .gitattributes | 36 ++ README.md | 76 ++++ chat_template.jinja | 89 ++++ config.json | 99 +++++ generation_config.json | 14 + model-00001-of-00013.safetensors | 3 + model-00002-of-00013.safetensors | 3 + model-00003-of-00013.safetensors | 3 + model-00004-of-00013.safetensors | 3 + model-00005-of-00013.safetensors | 3 + model-00006-of-00013.safetensors | 3 + model-00007-of-00013.safetensors | 3 + model-00008-of-00013.safetensors | 3 + model-00009-of-00013.safetensors | 3 + model-00010-of-00013.safetensors | 3 + model-00011-of-00013.safetensors | 3 + model-00012-of-00013.safetensors | 3 + model-00013-of-00013.safetensors | 3 + model.safetensors.index.json | 715 +++++++++++++++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 15 + 22 files changed, 1086 insertions(+) create mode 100644 ._README.md create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00013.safetensors create mode 100644 model-00002-of-00013.safetensors create mode 100644 model-00003-of-00013.safetensors create mode 100644 model-00004-of-00013.safetensors create mode 100644 model-00005-of-00013.safetensors create mode 100644 model-00006-of-00013.safetensors create mode 100644 model-00007-of-00013.safetensors create mode 100644 model-00008-of-00013.safetensors create mode 100644 model-00009-of-00013.safetensors create mode 100644 model-00010-of-00013.safetensors create mode 100644 model-00011-of-00013.safetensors create mode 100644 model-00012-of-00013.safetensors create mode 100644 model-00013-of-00013.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/._README.md b/._README.md new file mode 100644 index 0000000000000000000000000000000000000000..67884ca2a9f2096be0ff9178c74735780a76d49f GIT binary patch literal 4096 zcmeH~&2AGh5P&B^2oO@$3!G52mr7im{ogc=5K6j$S71?Apt&m#BRK z-h(ILF?a}09C?Z2&;TkN;6hIx$(|p3Y|rP@z}?69pbIcZYP~wO&a9nmWAH!^4`A=3 z*4p3u0?_Gc`!6zHE*IBZwi)nAXTAR|WqZ1g!w}#Rm1Q5Rs$l)ME!HShE|^~Gbo6)$ zaPVurWC~MMc(k6!FBB`^WUOYhT9yqs&Y?SshKStbI6BUBkd6FlJn<*-gv5i$CxPot z$k-2E63(Vm?|2Y-PB=`eB5#!AeCTw~_djP!Rn3uY(*oO+^)a`x%57P%P~?}Waw!@+ zqOKE$X-KFOQW7AiBpCz=@qO;5+&c_IhBlSr9jlvN3I<8)dk!V&VoHMHz$3#H1Hw2< zoG1uuT}-KQ@Ig^)Z2Jou;&%3?Ad`gD}~Z?+pwB!320lks%llEt;KX4&!^<| zh6$gXZm=lihWNVJ#R-|8oDp8RQNK*j_eX!0M>ACRzdR4_!$bIb{f%AyHQ(jVPVZFb z=}q5whJYbp2p9r}fFWQA7y^cXAz%pHGJ$Qk@}pyc-ZIM@t7eUCYsxGx>$Q~&#dO;# ig>IcLtb%c6B?XGL?uBppssH7=oAv*^;tBMwuD$^$G@@+) literal 0 HcmV?d00001 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..b3587d3 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +license: apache-2.0 +base_model: +- tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2 +library_name: mlx +tags: +- mlx +- quantized +- apple-silicon +- japanese +- swallow +language: +- ja +- en +pipeline_tag: text-generation +--- + +# Qwen3-Swallow-32B-RL-v0.2-MLX-fp16 + +This model is an [MLX](https://github.com/ml-explore/mlx) format conversion of [`tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2`](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2), optimized for Apple Silicon. + +## Model Details + +| Attribute | Value | +|---|---| +| **Original Model** | [`tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2`](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2) | +| **Architecture** | Dense Transformer | +| **Parameters** | 32B | +| **Quantization** | Full precision (fp16) | +| **Model Size** | ~61 GB | +| **Format** | MLX (Apple Silicon optimized) | +| **Converted with** | mlx-lm v0.30.8 | +| **License** | Apache 2.0 | + +## About Qwen3-Swallow + +Qwen3-Swallow is a bilingual Japanese-English large language model developed by the [Swallow Project](https://swallow-llm.github.io/) at the Institute of Science Tokyo (formerly Tokyo Institute of Technology) and AIST. Built upon Qwen3 through Continual Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Reinforcement Learning (RL), it achieves strong performance on both Japanese and English tasks while maintaining capabilities in mathematics and coding. + +For more details, see the [original model card](https://huggingface.co/tokyotech-llm/Qwen3-Swallow-32B-RL-v0.2). + +## Usage + +### Quick Start (Python) + +```python +from mlx_lm import load, generate + +model, tokenizer = load("tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-fp16") + +messages = [{"role": "user", "content": "hello"}] +prompt = tokenizer.apply_chat_template( + messages, add_generation_prompt=True +) + +response = generate(model, tokenizer, prompt=prompt, verbose=True, max_tokens=512) +``` + +### Interactive Chat + +```bash +mlx_lm.chat --model tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-fp16 +``` + +### OpenAI-Compatible Server + +```bash +mlx_lm.server --model tocchitocchi/Qwen3-Swallow-32B-RL-v0.2-MLX-fp16 --port 8080 +``` + +Then connect with any OpenAI-compatible client at `http://localhost:8080/v1`. + +## Acknowledgments + +- Original model by [Swallow Project](https://swallow-llm.github.io/) (Institute of Science Tokyo and AIST) +- MLX framework by [Apple Machine Learning Research](https://github.com/ml-explore/mlx) +- Conversion performed using [mlx-lm](https://github.com/ml-explore/mlx-lm) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- 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 + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b4bb4de --- /dev/null +++ b/config.json @@ -0,0 +1,99 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": [ + 151645, + 151643 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 25600, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.3", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b9efe0a --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.57.3", + "trust_remote_code": false +} diff --git a/model-00001-of-00013.safetensors b/model-00001-of-00013.safetensors new file mode 100644 index 0000000..fbe55f6 --- /dev/null +++ b/model-00001-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4743539f71497d7e8910a44b68bd2554c367ee2c2494bde08e74e80e9e89bbd +size 5194451684 diff --git a/model-00002-of-00013.safetensors b/model-00002-of-00013.safetensors new file mode 100644 index 0000000..e036c57 --- /dev/null +++ b/model-00002-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e1fbb77c6d78c0aff4f801f7fa758ed11f4445daa21be9769433bb75887a21 +size 5326899386 diff --git a/model-00003-of-00013.safetensors b/model-00003-of-00013.safetensors new file mode 100644 index 0000000..124f378 --- /dev/null +++ b/model-00003-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5cd7d763212fc0d957676eda5f03a7c22ca5ba28c9623ec5977e660e806768 +size 5138133828 diff --git a/model-00004-of-00013.safetensors b/model-00004-of-00013.safetensors new file mode 100644 index 0000000..7b5438e --- /dev/null +++ b/model-00004-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6202bcaaaa7ec45f12922a8ebba093dbdc8a72003080f9f4dc02954d74bb2c +size 5138133861 diff --git a/model-00005-of-00013.safetensors b/model-00005-of-00013.safetensors new file mode 100644 index 0000000..b627f95 --- /dev/null +++ b/model-00005-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36a64a0df445956467f266af6a06d03accbb3d3e98ec5f4f14efee17134d9d1a +size 5326899462 diff --git a/model-00006-of-00013.safetensors b/model-00006-of-00013.safetensors new file mode 100644 index 0000000..2a54c63 --- /dev/null +++ b/model-00006-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ef4ea137971cb7f07afa51c2076146e3f8cc96636503eb7a2d852147c653d2 +size 5138133863 diff --git a/model-00007-of-00013.safetensors b/model-00007-of-00013.safetensors new file mode 100644 index 0000000..de1c8e0 --- /dev/null +++ b/model-00007-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f120f6b037123031405e5ea88977f5e9206a3bd58e423428d1aa2966751ec2e4 +size 5138133867 diff --git a/model-00008-of-00013.safetensors b/model-00008-of-00013.safetensors new file mode 100644 index 0000000..d2396c4 --- /dev/null +++ b/model-00008-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44ac97fecb6a7ccfd781500e7d1d489bad9ffe9deb8838309dbba4df9c00cfd +size 5326899426 diff --git a/model-00009-of-00013.safetensors b/model-00009-of-00013.safetensors new file mode 100644 index 0000000..02a2695 --- /dev/null +++ b/model-00009-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242727519c1ea42118c2847d46ce379ddb45cd1c2ef26628b2a8022e64aba8bb +size 5138133847 diff --git a/model-00010-of-00013.safetensors b/model-00010-of-00013.safetensors new file mode 100644 index 0000000..2a3e1c5 --- /dev/null +++ b/model-00010-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f876d4c944c4bd3ee87535b8c247a12e84dcb92713561339f8392be4fefdc5 +size 5138133855 diff --git a/model-00011-of-00013.safetensors b/model-00011-of-00013.safetensors new file mode 100644 index 0000000..5df825d --- /dev/null +++ b/model-00011-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d91eed8de8b89b0d8743f56eff3b3630a184105bbab73033d705b01d81850b +size 5326899442 diff --git a/model-00012-of-00013.safetensors b/model-00012-of-00013.safetensors new file mode 100644 index 0000000..d1a2699 --- /dev/null +++ b/model-00012-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a67ce1a580fb8e5a5e8e06f325adb27443b4ca1a71228698664bd414bed5ca +size 5138133867 diff --git a/model-00013-of-00013.safetensors b/model-00013-of-00013.safetensors new file mode 100644 index 0000000..3529f64 --- /dev/null +++ b/model-00013-of-00013.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcc48ea840e6be7332181c41559ba6f502302012120d32d8848d22b694e0ee90 +size 3055341954 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3d9b8f4 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,715 @@ +{ + "metadata": { + "total_size": 65524246528, + "total_parameters": 32762123264 + }, + "weight_map": { + "lm_head.weight": "model-00013-of-00013.safetensors", + "model.embed_tokens.weight": "model-00001-of-00013.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors", + "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors", + "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors", + "model.norm.weight": "model-00013-of-00013.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..397f359 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": true, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "tool_parser_type": "json_tools", + "unk_token": null +}