commit 71709fffeb0c7421a24613d8eb501813ad0cf2df Author: ModelHub XC Date: Sun Sep 13 19:26:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: allura-org/Gemma-3-Glitter-12B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86bc1d9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,62 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 + +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +ComfyUI_02427_.png filter=lfs diff=lfs merge=lfs -text + +model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text + +model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text + +model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.model filter=lfs diff=lfs merge=lfs -text + +tokenizer_config.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/ComfyUI_02427_.png b/ComfyUI_02427_.png new file mode 100644 index 0000000..cced2b8 --- /dev/null +++ b/ComfyUI_02427_.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb05ac5d7c67f5c194dab515ab8ab6eb850022f77ba448ea140d049fa74cee62 +size 6596272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9036ce4 --- /dev/null +++ b/README.md @@ -0,0 +1,34 @@ +--- +base_model: +- ToastyPigeon/g3-12b-rp-system-v0.1 +- ToastyPigeon/g3-12b-storyteller-v0.2-textonly +- google/gemma-3-12b-it +library_name: transformers +tags: +- mergekit +- merge +--- +# ✨G3 Glitter 12B✨ +
+ +
+ +A creative writing model based on Gemma 3 12B IT. + +This is a 50/50 merge of two separate trains: +- [ToastyPigeon/g3-12b-rp-system-v0.1](https://huggingface.co/ToastyPigeon/g3-12b-rp-system-v0.1) - ~13.5M tokens of instruct-based training related to RP (2:1 human to synthetic) and examples using a system prompt. +- [ToastyPigeon/g3-12b-storyteller-v0.2-textonly](https://huggingface.co/ToastyPigeon/g3-12b-storyteller-v0.2-textonly) - ~20M tokens of completion training on long-form creative writing; 1.6M synthetic from R1, the rest human-created + +**Update**: Vision has returned to this model, rejoice. + +## Instruct Format + +Uses Gemma2/3 instruct, but has been trained to recognize an optional system role. +``` +system +{optional system turn with prompt} +user +{User messages; can also put sysprompt here to use the built-in g3 training} +model +{model response} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e17bde0 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "": 262144 +} diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..719b0cd --- /dev/null +++ b/chat_template.json @@ -0,0 +1,3 @@ +{ + "chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'model\n'}}\n{%- endif -%}\n" +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..4524de2 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "bos_token_id": 2, + "eoi_token_index": 256000, + "eos_token_id": 106, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "pad_token_id": 0, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "cache_implementation": "hybrid", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 3840, + "initializer_range": 0.02, + "intermediate_size": 15360, + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 16, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "sliding_window_pattern": 6, + "torch_dtype": "bfloat16", + "use_cache": true, + "vocab_size": 262208 + }, + "torch_dtype": "bfloat16", + "transformers_version": "4.50.0.dev0", + "unsloth_fixed": true, + "vision_config": { + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 896, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "torch_dtype": "bfloat16", + "vision_use_head": false + } +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..f60a673 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": [ + 1, + 106 + ], + "pad_token_id": 0, + "transformers_version": "4.50.0.dev0" +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..0cdc2f7 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,10 @@ +models: + - model: ToastyPigeon/g3-12b-rp-system-v0.1 + parameters: + weight: 0.5 + - model: ToastyPigeon/g3-12b-storyteller-v0.2-textonly + parameters: + weight: 0.5 +merge_method: linear +dtype: bfloat16 +tokenizer_source: unsloth/gemma-3-12b-it \ No newline at end of file diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..42f5899 --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d81af47f9085a53ec93c9753a9cc7f289ea6d88d5ed5769897fcc3673e07457 +size 4979902160 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..a940fee --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970a07d33a4b58765c06c17733170b025e5597ce003d2b19c6d0c5c281219b35 +size 4931296560 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..cc59365 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc091db1d0e176d0f9f403f529d286f66f9c5eaad266a259851c6f5a95dd9b4 +size 4931296624 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..a8fc6b9 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f79da97883ea1db154235414cbaae4398916fe8cc49179e0c29bfe962428292 +size 4931296624 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..8bcdc88 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbbaa3ec46b178df7aa5736ccbfd9ce7395dfc933f333f472937f15730b3244 +size 4601000896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..c5eb054 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1072 @@ +{ + "metadata": { + "total_size": 24374650080 + }, + "weight_map": { + "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.post_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.pre_feedforward_layernorm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.37.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.37.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.37.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.4.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.4.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "language_model.model.layers.40.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.41.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.42.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.43.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.44.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.45.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.46.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.input_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.post_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.pre_feedforward_layernorm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.k_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.q_norm.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.47.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.post_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.pre_feedforward_layernorm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "language_model.model.norm.weight": "model-00005-of-00005.safetensors", + "multi_modal_projector.mm_input_projection_weight": "model-00001-of-00005.safetensors", + "multi_modal_projector.mm_soft_emb_norm.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00005.safetensors", + "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00005.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..b1e00fc --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,29 @@ +{ + "do_convert_rgb": null, + "do_normalize": true, + "do_pan_and_scan": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Gemma3ImageProcessor", + "image_seq_length": 256, + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "pan_and_scan_max_num_crops": null, + "pan_and_scan_min_crop_size": null, + "pan_and_scan_min_ratio_to_activate": null, + "processor_class": "Gemma3Processor", + "resample": 2, + "rescale_factor": 0.00392156862745098, + "size": { + "height": 896, + "width": 896 + } +} diff --git a/processor_config.json b/processor_config.json new file mode 100644 index 0000000..453c796 --- /dev/null +++ b/processor_config.json @@ -0,0 +1,4 @@ +{ + "image_seq_length": 256, + "processor_class": "Gemma3Processor" +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..bdd437b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "boi_token": "", + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eoi_token": "", + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "image_token": "", + "pad_token": { + "content": "", + "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..29401f9 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795 +size 33384568 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..14f810a --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c +size 4689074 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..2732cf3 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05efef20252f174e2220f376a03794e905f425178008e06ca3cbecbfff669752 +size 1157008