commit e80f5e3e638881883f835259e950f9c982e62d60 Author: ModelHub XC Date: Tue Sep 1 20:47:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jhu-clsp/rank1-14b-awq Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2fc868 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..93d4eb9 --- /dev/null +++ b/README.md @@ -0,0 +1,235 @@ +--- +license: mit +datasets: +- jhu-clsp/rank1-training-data +base_model: +- jhu-clsp/rank1-14b +pipeline_tag: text-generation +tags: +- reranker +- retrieval +- quantized +- awq +language: +- en +--- + +# rank1-14b-awq: Quantized Model for Test-Time Compute Reranking + +📄 [Paper](https://arxiv.org/abs/2502.18418) | 🚀 [GitHub Repository](https://github.com/orionw/rank1) + +rank1-14b-awq is a quantized version of the rank1-14b model. This AWQ-quantized 14B parameter model maintains the reasoning capabilities of the original model while requiring less memory and providing faster inference. The model is trained from the Qwen2.5-14B base model and leverages test-time compute to generate reasoning chains before deciding if a document is relevant to a query. + +## Model Description + +rank1 introduces a novel approach to information retrieval by generating explicit reasoning chains before making relevance judgments. Unlike traditional rerankers that directly output scores, rank1: + +1. Receives a query and document pair +2. Generates a reasoning chain within a `...` section +3. Makes a binary relevance judgment (`true` or `false`) +4. Returns a confidence score based on the logits of the true/false tokens + +This approach helps the model break down complex relevance decisions into logical steps, improving performance across diverse retrieval tasks. + +## Quantization Details + +This model uses Activation-aware Weight Quantization (AWQ) to reduce the model size while maintaining performance. Compared to the full-precision model, this quantized version: + +- Requires less GPU memory +- Offers faster inference times +- Maintains comparable accuracy on retrieval tasks + +## Model Family + +| Model | Base | Description | +|:------|:-----|:------------| +| [rank1-7b](https://huggingface.co/jhu-clsp/rank1-7b) | Qwen2.5-7B | Smaller variant (7B parameters) | +| [rank1-14b](https://huggingface.co/jhu-clsp/rank1-14b) | Qwen2.5-14B | Full-precision version (14B parameters) | +| [rank1-32b](https://huggingface.co/jhu-clsp/rank1-32b) | Qwen2.5-32B | Largest variant (32B parameters) | +| [rank1-mistral-2501-24b](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b) | Mistral-Small 2501 24B | Trained from Mistral base | +| [rank1-llama3-8b](https://huggingface.co/jhu-clsp/rank1-llama3-8b) | Llama 3.1 8B | Trained from Llama 3.1 base | + +### Quantized Variants + +| Model | Description | +|:------|:------------| +| [rank1-7b-awq](https://huggingface.co/jhu-clsp/rank1-7b-awq) | Quantized version of rank1-7b | +| [rank1-14b-awq](https://huggingface.co/jhu-clsp/rank1-14b-awq) | Current model - Quantized version of rank1-14b | +| [rank1-32b-awq](https://huggingface.co/jhu-clsp/rank1-32b-awq) | Quantized version of rank1-32b | +| [rank1-mistral-2501-24b-awq](https://huggingface.co/jhu-clsp/rank1-mistral-2501-24b-awq) | Quantized version of rank1-mistral-24b | +| [rank1-llama3-8b-awq](https://huggingface.co/jhu-clsp/rank1-llama3-8b-awq) | Quantized version of rank1-llama3-8b | + +## Associated Data and Resources + +| Resource | Description | +|:---------|:------------| +| [rank1-r1-msmarco](https://huggingface.co/datasets/jhu-clsp/rank1-r1-msmarco) | All R1 output examples from MS MARCO | +| [rank1-training-data](https://huggingface.co/datasets/jhu-clsp/rank1-training-data) | Training data used for rank1 models | +| [rank1-run-files](https://huggingface.co/datasets/jhu-clsp/rank1-run-files) | Pre-computed run files for use in top 100 doc reranking | +| [GitHub Repository](https://github.com/orionw/rank1) | Official rank1 repository | + +## Usage +Note that official usage is found on the Github and accounts for edge cases. But for simple use cases the minimal example below works. + +
+Click to expand: Minimal example with vLLM + +```python +from vllm import LLM, SamplingParams +import math + +# Initialize the model with vLLM +model = LLM( + model="jhu-clsp/rank1-14b-awq", + tensor_parallel_size=1, # Number of GPUs + trust_remote_code=True, + max_model_len=16000, # Context length + gpu_memory_utilization=0.9, + dtype="auto", # Will use the appropriate quantized dtype +) + +# Set up sampling parameters +sampling_params = SamplingParams( + temperature=0, + max_tokens=8192, + logprobs=20, + stop=[" true", " false"], + skip_special_tokens=False +) + +# Prepare the prompt +def create_prompt(query, document): + return ( + "Determine if the following passage is relevant to the query. " + "Answer only with 'true' or 'false'.\n" + f"Query: {query}\n" + f"Passage: {document}\n" + "" + ) + +# Example usage +query = "What are the effects of climate change?" +document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities." + +# Generate prediction +prompt = create_prompt(query, document) +outputs = model.generate([prompt], sampling_params) + +# Extract score +output = outputs[0].outputs[0] +text = output.text +final_logits = output.logprobs[-1] + +# Get token IDs for "true" and "false" tokens +from transformers import AutoTokenizer +tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-14b-awq") +true_token = tokenizer(" true", add_special_tokens=False).input_ids[0] +false_token = tokenizer(" false", add_special_tokens=False).input_ids[0] + +# Calculate relevance score (probability of "true") +true_logit = final_logits[true_token].logprob +false_logit = final_logits[false_token].logprob +true_score = math.exp(true_logit) +false_score = math.exp(false_logit) +relevance_score = true_score / (true_score + false_score) + +print(f"Reasoning chain: {text}") +print(f"Relevance score: {relevance_score}") +``` + +
+ +
+Click to expand: Usage with AutoGPTQ/AWQ + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +# Load the tokenizer and quantized model +tokenizer = AutoTokenizer.from_pretrained("jhu-clsp/rank1-14b-awq") +model = AutoModelForCausalLM.from_pretrained( + "jhu-clsp/rank1-14b-awq", + device_map="auto", + trust_remote_code=True +) + +# Prepare the prompt +query = "What are the effects of climate change?" +document = "Climate change leads to rising sea levels, extreme weather events, and disruptions to ecosystems. These effects are caused by increasing greenhouse gas concentrations in the atmosphere due to human activities." + +prompt = f"Determine if the following passage is relevant to the query. Answer only with 'true' or 'false'.\nQuery: {query}\nPassage: {document}\n" + +# Generate the reasoning chain and relevance judgment +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) +with torch.no_grad(): + outputs = model.generate( + **inputs, + max_new_tokens=512, + temperature=0.0, + return_dict_in_generate=True, + output_scores=True, + pad_token_id=tokenizer.eos_token_id + ) + +# Process the output +generated_text = tokenizer.decode(outputs.sequences[0], skip_special_tokens=False) +reasoning_chain = generated_text.split("")[1].split("")[0].strip() +relevance_judgment = "true" if "true" in generated_text.split("")[1].strip().lower() else "false" + +print(f"Reasoning chain: {reasoning_chain}") +print(f"Relevance judgment: {relevance_judgment}") +``` + +
+ +## Performance + +rank1-14b-awq demonstrates strong performance on retrieval benchmarks while offering faster inference and lower memory requirements than the full-precision model. The quantization process preserves the model's ability to "think through" relevance decisions, making it effective for nuanced topics. + +For specific benchmark results and comparisons with other models, please refer to the paper and the official GitHub repository. + +## Installation + +Please see the Github for detailed installation instructions. + +## MTEB Integration + +rank1 is compatible with the [MTEB benchmarking framework](https://github.com/embeddings-benchmark/mteb): + +```python +from mteb import MTEB +from rank1 import rank1 # From the official repo + +# Initialize the model +model = rank1( + model_name_or_path="jhu-clsp/rank1-14b-awq", + num_gpus=1, + device="cuda", + quantized=True # Indicate that you're using the quantized version +) + +# Run evaluation on specific tasks +evaluation = MTEB(tasks=["NevIR"]) +results = evaluation.run(model) +``` + +## Citation + +If you use rank1 in your research, please cite our work: + +```bibtex +@misc{weller2025rank1testtimecomputereranking, + title={Rank1: Test-Time Compute for Reranking in Information Retrieval}, + author={Orion Weller and Kathryn Ricci and Eugene Yang and Andrew Yates and Dawn Lawrie and Benjamin Van Durme}, + year={2025}, + eprint={2502.18418}, + archivePrefix={arXiv}, + primaryClass={cs.IR}, + url={https://arxiv.org/abs/2502.18418}, +} +``` + +## License + +[MIT License](https://github.com/orionw/rank1/blob/main/LICENSE) \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..2c67f0f --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,26 @@ +{ + "": 151666, + "": 151658, + "": 151665, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..21d884d --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "_name_or_path": "/home/oweller2/my_scratch/cache/hub/models--orionweller--c1-14b/snapshots/6f753c1e2adc253cfb7508cb5ec948ebba8b5205", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 131072, + "max_window_layers": 48, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "quantization_config": { + "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": "float16", + "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..612a232 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": 151643, + "max_new_tokens": 8192, + "transformers_version": "4.47.1" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..8409cd4 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bcf81ed6163169d9906e29957739c35313bd53dae44e35b4056d73da7784f2 +size 3988804408 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..c018ac6 --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35c459711da42d07b8e1c46f963bb693b22b24074c43c450095c34ee3a12b92 +size 3968309440 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..69f9d7d --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b71f0b5855fd36483e8e72fb56955d1d4518c0c816dab7f31fa517ff281a8b39 +size 2023056736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..2865a8e --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1258 @@ +{ + "metadata": { + "total_size": 9980028928 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.down_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.up_proj.qweight": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.down_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.qweight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.qzeros": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors", + "lm_head.weight": "model-00003-of-00003.safetensors" + } +} \ No newline at end of file diff --git a/quant_config.json b/quant_config.json new file mode 100644 index 0000000..01a8401 --- /dev/null +++ b/quant_config.json @@ -0,0 +1,6 @@ +{ + "zero_point": true, + "q_group_size": 128, + "w_bit": 4, + "version": "GEMM" +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..fa1b2f9 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,33 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>", + "", + "" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..0d5bc1c --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbbede8a5db70ed006fa645af44ebd6a069c667d16bb9e7a0d00a5a6dc7111e +size 11422265 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..88b72d1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,227 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "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 + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>", + "", + "" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833