commit edc3bb562fbd947daaaf7b180ff0247088b9bd3f Author: ModelHub XC Date: Wed Sep 2 08:30:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: inarikami/DeepSeek-R1-Distill-Qwen-32B-AWQ Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..26dfb80 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..94a50fe --- /dev/null +++ b/README.md @@ -0,0 +1,54 @@ +--- +license: mit +pipeline_tag: text-generation +tags: +- code +- deepseek_v3 +- qwen +- int4 +- conversational +base_model: +- deepseek-ai/DeepSeek-R1-Distill-Qwen-32B +--- + +# DeepSeek-R1-Distill-Qwen-32B-AWQ wint4 + +Distillation of DeepSeek-R1 to Qwen 32B, quantized using AWQ to wint4. It fits on any 24GB VRAM GPU or 32GB URAM device! + +## MMLU-PRO + +The MMLU-PRO dataset evaluates subjects across 14 distinct fields using a 5-shot accuracy measurement. Each task assesses models following the methodology of the original MMLU implementation, with each having ten possible choices. + +### Measure + +- **Accuracy**: Evaluated as "exact_match" + +### Shots + +- **Shots**: 5-shot + +### Tasks + +| Tasks | Filter | n-shot | Metric | Value | Stderr | +|------------------|---------------|--------|-------------|--------|--------| +| mmlu_pro | custom-extract| | exact_match | 0.5875 | 0.0044 | +| biology | custom-extract| 5 | exact_match | 0.7978 | 0.0150 | +| business | custom-extract| 5 | exact_match | 0.5982 | 0.0175 | +| chemistry | custom-extract| 5 | exact_match | 0.4691 | 0.0148 | +| computer_science | custom-extract| 5 | exact_match | 0.6122 | 0.0241 | +| economics | custom-extract| 5 | exact_match | 0.7346 | 0.0152 | +| engineering | custom-extract| 5 | exact_match | 0.3891 | 0.0157 | +| health | custom-extract| 5 | exact_match | 0.6345 | 0.0168 | +| history | custom-extract| 5 | exact_match | 0.6168 | 0.0249 | +| law | custom-extract| 5 | exact_match | 0.4596 | 0.0150 | +| math | custom-extract| 5 | exact_match | 0.6425 | 0.0130 | +| other | custom-extract| 5 | exact_match | 0.6223 | 0.0160 | +| philosophy | custom-extract| 5 | exact_match | 0.5731 | 0.0222 | +| physics | custom-extract| 5 | exact_match | 0.5073 | 0.0139 | +| psychology | custom-extract| 5 | exact_match | 0.7494 | 0.0154 | + +### Groups + +| Groups | Filter | n-shot | Metric | Value | Stderr | +|----------|---------------|--------|-------------|--------|--------| +| mmlu_pro | custom-extract| | exact_match | 0.5875 | 0.0044 | \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..9225cba --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "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": 27648, + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "quantization_config": { + "bits": 4, + "group_size": 128, + "modules_to_not_convert": null, + "quant_method": "awq", + "version": "gemm", + "zero_point": true + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.47.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..d079819 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": 151643, + "transformers_version": "4.47.1", + "use_cache": false +} diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..2e09c00 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d79c869a5d7cadbdd5b4da65675c016f96e88e6f958cdd582156e2b27021d42 +size 4956994936 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..5844d6a --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3151e79bac67a100e736a0d70cf54d71e939c8fbce83ed58754a4c7901ee2cd5 +size 4993553856 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..6db9c52 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e8a61bffc6b3d5142d526ede7e7c665d6dc112bf04a9bd031816869f855093e +size 4960831008 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..89f5a85 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa54fc028152506871af834f2b783c32fc6e8a919a26739057ba8f55182810a +size 4417614320 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..d6493ab --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1674 @@ +{ + "metadata": { + "total_size": 19328804864 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00004.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.48.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.48.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.49.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.49.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.50.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.50.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.down_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.down_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.51.mlp.down_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.51.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.self_attn.o_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.gate_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.up_proj.qweight": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.up_proj.qzeros": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.up_proj.scales": "model-00003-of-00004.safetensors", + "model.layers.52.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.52.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.52.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.53.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.53.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.54.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.54.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.55.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.55.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.56.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.56.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.57.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.57.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.58.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.58.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.59.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.59.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.60.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.60.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.61.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.61.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.62.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.62.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.self_attn.o_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.gate_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.up_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.qweight": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.qzeros": "model-00004-of-00004.safetensors", + "model.layers.63.mlp.down_proj.scales": "model-00004-of-00004.safetensors", + "model.layers.63.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors", + "lm_head.weight": "model-00004-of-00004.safetensors" + } +} \ 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..1a2db24 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893 +size 11422778 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b068ffc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,195 @@ +{ + "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, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}