commit d5718b1227e0bcfb952473145634fbe8c12ee9df Author: ModelHub XC Date: Fri May 1 05:41:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-quant Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..367082a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-fp16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-fp16.gguf b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-fp16.gguf new file mode 100644 index 0000000..a342757 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f7d943034a95e996ac46a4eb769509298dfe03514d3e97fb124cde14cc35f0b +size 29547715808 diff --git a/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q4_k_m.gguf b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q4_k_m.gguf new file mode 100644 index 0000000..fcce5c9 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e2558e9e72e47a20a5d54f7ea56dd49ed1ac6d717d12216f5b2da9b5ce560c +size 8988110048 diff --git a/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q8_0.gguf b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q8_0.gguf new file mode 100644 index 0000000..b8ec9ee --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b350c4e323ecd169ad1cc1512797fa80fdf1203899a63bf444771290227de2 +size 15701597408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5e830d7 --- /dev/null +++ b/README.md @@ -0,0 +1,12 @@ +--- +library_name: transformers +license: mit +language: +- ja +base_model: +- flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat +--- + +# Model Card for Model ID + +This is repository of different quantinization of [DeepSeek-R1-Distill-Qwen-14B-Japanese-chat](https://huggingface.co/flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat). Please refer to the orginal model card for more details. diff --git a/config.json b/config.json new file mode 100644 index 0000000..924c69f --- /dev/null +++ b/config.json @@ -0,0 +1,44 @@ +{ + "_name_or_path": "flypg/DeepSeek-R1-Distill-Qwen-14B-Japanese-chat", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "quantization_config": { + "_load_in_4bit": false, + "_load_in_8bit": true, + "bnb_4bit_compute_dtype": "float32", + "bnb_4bit_quant_storage": "uint8", + "bnb_4bit_quant_type": "fp4", + "bnb_4bit_use_double_quant": false, + "llm_int8_enable_fp32_cpu_offload": false, + "llm_int8_has_fp16_weight": false, + "llm_int8_skip_modules": null, + "llm_int8_threshold": 6.0, + "load_in_4bit": true, + "load_in_8bit": false, + "quant_method": "bitsandbytes" + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.48.3", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..aa81b12 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.48.3" +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..c318730 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a57423409797bfa278326902d120011af3f1ec70246ea8c463fd40eaa8af2c +size 4996578705 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..da122a2 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c56c311292bf106a79deb363afb63bfcd6ad81a4b57c7414f890e9be1c7853a +size 4958443366 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..de7ee91 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec186a56d42a028b80561be7ea58339ad599a8fc5e4e813dd8a3704e0d5f178e +size 4824639489 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..afcbf2b --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc8182780a9605acbd87edbfe360569962f73b65e0304c212c18ae6a3a9d899 +size 1557135488 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..60e702a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1258 @@ +{ + "metadata": { + "total_size": 16336660816 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.SCB": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight_format": "model-00002-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.SCB": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.weight_format": "model-00003-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight_format": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight_format": "model-00001-of-00004.safetensors", + "model.norm.weight": "model-00003-of-00004.safetensors" + } +} diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..a67ad45 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +accelerate==1.4.0 +bitsandbytes==0.45.2 +typing_extensions==4.12.2 \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a1c9eec --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5aef614e5d3425ddd97623eabba0f904b5fa77c8db08d3624e4721dae7323a +size 11423069 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7b5c60c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,202 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "max_length": 512, + "model_max_length": 16384, + "pad_to_multiple_of": null, + "pad_token": "<｜end▁of▁sentence｜>", + "pad_token_type_id": 0, + "padding_side": "left", + "sp_model_kwargs": {}, + "stride": 0, + "tokenizer_class": "LlamaTokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": null, + "use_default_system_prompt": false +}