commit c7cdc0c461baba69f5de028853ada15d9b2f4e27 Author: ModelHub XC Date: Sat Oct 17 05:24:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: inclusionAI/Qwen3-32B-AWorld Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3cd7649 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,65 @@ +*.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 + +*.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 +model-00006-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00013-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00009-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00014-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00012-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00008-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00007-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00010-of-00014.safetensors filter=lfs diff=lfs merge=lfs -text +model-00011-of-00014.safetensors 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..e24fe02 --- /dev/null +++ b/README.md @@ -0,0 +1,134 @@ +--- +license: apache-2.0 +base_model: +- Qwen/Qwen3-32B +library_name: transformers +--- + + + +
+ +| | | +|-|-| +| [![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/inclusionAI/AWorld/tree/main/train) | [![arXiv](http://img.shields.io/badge/cs.AI-arXiv%3A2508.20404-B31B1B.svg?logo=arxiv&logoColor=red)](https://arxiv.org/abs/2508.20404) | + +
+ +# Qwen3-32B-AWorld + +## Model Description + +**Qwen3-32B-AWorld** is a large language model fine-tuned from `Qwen3-32B`, specializing in agent capabilities and proficient tool usage. The model excels at complex agent-based tasks through precise integration with external tools, achieving a pass@1 score on the GAIA benchmark that surpasses GPT-4o and is comparable to DeepSeek-V3. + + + +## Quick Start + +This guide provides instructions for quickly deploying and running inference with `Qwen3-32B-AWorld` using vLLM. + +### Deployment with vLLM + +To deploy the model, use the following `vllm serve` command: + +```bash +vllm serve inclusionAI/Qwen3-32B-AWorld \ +--rope-scaling '{"rope_type":"yarn","factor":4.0,"original_max_position_embeddings":32768}' \ +--max-model-len 131072 \ +--gpu-memory-utilization 0.85 \ +--dtype bfloat16 \ +--tensor-parallel-size 8 \ +--enable-auto-tool-choice \ +--tool-call-parser hermes +``` + +**Key Configuration:** + +* **Deployment Recommendation:** We recommend deploying the model on **8 GPUs** to enhance concurrency. The `tensor-parallel-size` argument should be set to the number of GPUs you are using (e.g., `8` in the command above). +* **Tool Usage Flags:** To enable the model's tool-calling capabilities, it is crucial to include the `--enable-auto-tool-choice` and `--tool-call-parser hermes` flags. These ensure that the model can correctly process tool calls and parse the results. + +### Making Inference Calls + +When making an inference request, you must include the `tools` you want the model to use. The format should follow the official OpenAI API specification. + +Here is a complete Python example for making an API call to the deployed model using the requests library. This example demonstrates how to query the model with a specific tool. + +```python +import requests +import json + +# Define the tools available for the model to use +tools = [ + { + "type": "function", + "function": { + "name": "mcp__google-search__search", + "description": "Perform a web search query", + "parameters": { + "type": "object", + "properties": { + "query": { + "description": "Search query", + "type": "string" + }, + "num": { + "description": "Number of results (1-10)", + "type": "number" + } + }, + "required": [ + "query" + ] + } + } + } +] + +# Define the user's prompt +messages = [ + { + "role": "user", + "content": "Search for hangzhou's weather today." + } +] + +# Set generation parameters +temperature = 0.6 +top_p = 0.95 +top_k = 20 +min_p = 0 + +# Prepare the request payload +data = { + "messages": messages, + "tools": tools, + "temperature": temperature, + "top_p": top_p, + "top_k": top_k, + "min_p": min_p, +} + +# The endpoint for the vLLM OpenAI-compatible server +# Replace {your_ip} and {your_port} with the actual IP address and port of your server. +url = "http://{your_ip}:{your_port}/v1/chat/completions" + +# Send the POST request +response = requests.post( + url, + headers={"Content-Type": "application/json"}, + data=json.dumps(data) +) + +# Print the response from the server +print("Status Code:", response.status_code) +print("Response Body:", response.text) + +``` + +**Note:** + +* Remember to replace `{your_ip}` and `{your_port}` in the `url` variable with the actual IP address and port where your vLLM server is running. The default port is typically `8000`. \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|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..40ff5ea --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 25600, + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen3", + "num_attention_heads": 64, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.1", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..f9291c3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"text-generation"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e58a45f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "4.51.1" +} 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-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..c47efc2 --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce783809c32e996af78a949a7f49dfefad5ead9d6d4ce093eb525d489b6d4708 +size 4932307584 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..9619cee --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b071cb8d7505ab0f10781809b068df3c22b8129250c74befa5ba049acee23cc0 +size 4875989696 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..4a638b4 --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7ae1d67444db569c07be8a591fd3a9226dc64ded855817cd85f8d3c3f5bd6e +size 4875989720 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..cf98f8c --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394263b75b848e65fbf3b754099a538a9b51bbc8ddbfd44367b2ab3a574c32a8 +size 4875989752 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..c7efa0c --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f2b74b2a3db95f4e608ca42b50b0130565dc2cd88be6202194e1dd915e52b0 +size 4875989752 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..213718a --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cecebffda43e9750dc4fec01572063376fe6c10938d5088195eee08411665769 +size 4875989752 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..b626bd3 --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd1d06efcfef74c08426cfef9fdb0a4b02c3f7aba4498c135016411af90aa9cd +size 4875989752 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..7467457 --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee5623d08be73bc7beffdfd349a52b0ad9ea78c3f0194b492ab17939ccfd752 +size 4875989752 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..722a862 --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8659a24856264610b7d270306bfaf331e89389fdc5ef55db3d01a2e560ea62fb +size 4875989752 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..133cafa --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee407622ee57d2553fd14c7f17705ec257f5fd36002b7e9a380fb21bb15f63a6 +size 4875989752 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..e8dcc84 --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638438a9823c6b08affa7907a5b088bd485edd5543b0beeea0c525279c5afa96 +size 4875989752 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..5514a6f --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e0bc2b3579a26426917b803b0e64d6c9698ff0ca8bec5dc79e90c1f2790c9a +size 4875989752 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..e4ffff6 --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8dabf0501b66875ba6d93d51588067aad61d7f34da0d82b0676f9ed7f7bc09e +size 4875989752 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..73446b9 --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9421878955d952869fe1263e0e3d46135296e03b091cc5e8e0d9bd377721c35 +size 2080144040 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..243012f --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,714 @@ +{ + "metadata": { + "total_size": 65524246528 + }, + "weight_map": { + "lm_head.weight": "model-00014-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.norm.weight": "model-00014-of-00014.safetensors" + } +} diff --git a/qwen3-32b-aworld-performance.jpg b/qwen3-32b-aworld-performance.jpg new file mode 100644 index 0000000..aeda175 Binary files /dev/null and b/qwen3-32b-aworld-performance.jpg differ diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "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": "<|im_end|>", + "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..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7345216 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,240 @@ +{ + "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": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "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\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('') and message.content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in message.content %}\n {%- set content = message.content.split('')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '\\n\\n\\n\\n' }}\n {%- endif %}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "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