commit 482930d126b47679b854953bf6004955d66432a5 Author: ModelHub XC Date: Fri Jul 10 17:59:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: LeaderboardModel1/zeta-2.1-autoround-W4A16 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..43c91e6 --- /dev/null +++ b/README.md @@ -0,0 +1,117 @@ +--- +base_model: +- zed-industries/zeta-2.1 +pipeline_tag: text-generation +tags: +- quantized +- w4a16 +- autoround +- low-bit-open-llm-leaderboard +--- + +# zeta-2.1-autoround-W4A16 + +## Model Details + +This model is a int4 weight-only quantization with group_size 128 and symmetric quantization of [zed-industries/zeta-2.1](https://huggingface.co/zed-industries/zeta-2.1) generated by [AutoRound](https://github.com/intel/auto-round). Please follow the license of the original model. + +## Quantization Details + +| Attribute | Value | +|-----------|-------| +| Base Model | [zed-industries/zeta-2.1](https://huggingface.co/zed-industries/zeta-2.1) | +| Quantization Tool | [AutoRound](https://github.com/intel/auto-round) | +| Quantization Scheme | W4A16 | +| Quantized Size | 5954 MB | + +## Evaluation Results + +| Task | Accuracy | +|------|----------| +| hellaswag | 0.4077 | +| mmlu | 0.3676 | +| piqa | 0.6768 | + +## How to Use + +### HF Usage + +**Step 1: Install [AutoRound](https://github.com/intel/auto-round)** + +```bash +pip install auto-round +``` + +**Step 2: Load and run the quantized model** + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "zeta-2.1-autoround-W4A16" + +# load the tokenizer and the model +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto") + +# prepare the model input +prompt = "Write a quick sort algorithm." +messages = [{"role": "user", "content": prompt}] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +# conduct text completion +generated_ids = model.generate(**model_inputs, max_new_tokens=512) +output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :].tolist() + +content = tokenizer.decode(output_ids, skip_special_tokens=True) +print("content:", content) +``` + +### VLLM Usage + +```bash +vllm serve zeta-2.1-autoround-W4A16 \ + --trust-remote-code \ + --dtype bfloat16 \ + --tensor_parallel_size 1 +``` + +If you encounter any issues, feel free to open an issue on the [AutoRound GitHub repo](https://github.com/intel/auto-round/issues) or provide feedback on the [Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard). + +## Ethical Considerations and Limitations + +The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs. +Therefore, before deploying any applications of the model, developers should perform safety testing. + +## Caveats and Recommendations + +Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. +Here are a couple of useful links to learn more about Intel's AI software: + +- [Intel Neural Compressor](https://github.com/intel/neural-compressor) +- [AutoRound](https://github.com/intel/auto-round) + +## Disclaimer + +The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes. + +## Cite + +``` +@article{cheng2023optimize, + title={Optimize weight rounding via signed gradient descent for the quantization of llms}, + author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, + journal={arXiv preprint arXiv:2309.05516}, + year={2023} +} +``` + +[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round) + +--- + +*This model is part of the [Intel Low-Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard) initiative.* diff --git a/config.json b/config.json new file mode 100644 index 0000000..1e9c8f9 --- /dev/null +++ b/config.json @@ -0,0 +1,45 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "bos_token_id": 0, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.009882118, + "intermediate_size": 14336, + "layer_norm_eps": null, + "max_position_embeddings": 32768, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 1, + "pretraining_tp": 1, + "quantization_config": { + "autoround_version": "0.12.3", + "bits": 4, + "data_type": "int", + "group_size": 128, + "iters": 0, + "packing_format": "auto_round:auto_gptq", + "quant_method": "auto-round", + "sym": true + }, + "resid_pdrop": 0.1, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 500000.0, + "rope_type": "default" + }, + "tie_word_embeddings": false, + "transformers_version": "5.9.0", + "unsloth_version": "2026.1.3", + "use_cache": true, + "vocab_size": 155136 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..5a21245 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "do_sample": true, + "eos_token_id": 2, + "pad_token_id": 1, + "transformers_version": "5.9.0", + "use_cache": true +} diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..a4cec44 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2793d00ee9c03b67c7df1fd69d995ba071e36e5351595f58fc0d6e94ae5e0597 +size 1072275792 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..e34d493 --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47022d17786fed21651e0677c5cf05878de899d724eaa82001a44fc1bf139c26 +size 1050483896 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..91a1bc1 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1398dc666e6048361d3647f068c5b37961b22bab7aa89387fa0709fe3749cff +size 1072292648 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..f2f06ff --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b9ba22c695f27ed8222ab7571a1970461dc1470c773971bc363f3f1c586308 +size 431530768 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..5937260 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02462556e3d4668a19c0cbb0d07142cedf2c1e91c5a8109764cd82e76e9b8982 +size 1270874224 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..345050a --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4105ab5a54a0c2e7719fc9337dfe7fd7bf404801f6e51363ed9cc9a9f4a522a7 +size 8280 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..1b677b6 --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd69654339c944795df0dd9b2ee2c07bdd3522f5d4074c47bbe3c87a17ad291 +size 1270874208 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..9064be7 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,749 @@ +{ + "metadata": { + "format": "safetensors", + "total_shards": 7, + "total_parameters": 2204897280, + "total_size": 6168256512 + }, + "weight_map": { + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00007.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00002-of-00007.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00003-of-00007.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00003-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00004-of-00007.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00004-of-00007.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.embed_tokens.weight": "model-00005-of-00007.safetensors", + "model.norm.weight": "model-00006-of-00007.safetensors", + "lm_head.weight": "model-00007-of-00007.safetensors" + } +} \ No newline at end of file diff --git a/quantization_config.json b/quantization_config.json new file mode 100644 index 0000000..e9212ed --- /dev/null +++ b/quantization_config.json @@ -0,0 +1,10 @@ +{ + "bits": 4, + "data_type": "int", + "group_size": 128, + "sym": true, + "iters": 0, + "autoround_version": "0.12.3", + "quant_method": "auto-round", + "packing_format": "auto_round:auto_gptq" +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..13d7916 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6520146c388c495a98bbea62ff6d00c0a8935bed33622e33bb33ec71aaafed +size 11891696 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d1033bd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,13 @@ +{ + "backend": "tokenizers", + "bos_token": "<[begin▁of▁sentence]>", + "clean_up_tokenization_spaces": false, + "eos_token": "<[end▁of▁sentence]>", + "is_local": false, + "local_files_only": false, + "model_max_length": 32768, + "pad_token": "<[PAD▁TOKEN]>", + "padding_side": "left", + "sep_token": "<[SEP▁TOKEN]>", + "tokenizer_class": "TokenizersBackend" +}