commit e9d4ac6df0259dce61ccda19d8fc6b53b95de647 Author: ModelHub XC Date: Wed May 27 05:34:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MediaTek-Research/Breeze-7B-FC-v1_0 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ddf758c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +pytorch_model-00001-of-00004.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00002-of-00004.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00003-of-00004.bin filter=lfs diff=lfs merge=lfs -text +pytorch_model-00004-of-00004.bin filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a41a3eb --- /dev/null +++ b/README.md @@ -0,0 +1,234 @@ +--- +license: apache-2.0 +extra_gated_prompt: "We will release in the nearly future." +extra_gated_fields: + Name: text + Company: text + Title: text +--- + +# Model Card for MediaTek Research Breeze-7B-FC-v1_0 + +MediaTek Research Breeze-7B-FC (hereinafter referred to as Breeze-7B-FC) is an advanced language model developed by MediaTek Research, building on [Breeze-7B-Base](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v1_0). Breeze-7B-FC extends its predecessor by incorporating a key feature: function calling. These enhancements make Breeze-7B-FC more versatile and capable of handling a wider range of tasks efficiently. + + +## 🏆 Performance + +| Models | #Parameters | Organization | License | 🧰 Function Calling? | 💬 Instrustion Following? | +|--------------------------------------------------------------------------------------------|-------------|------------|------------|-------------------|----------| +| [Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0)| 7B | MediaTek Research | Apache 2.0 | ❌ | ✅ | +| [**Breeze-7B-FC-v1_0**](https://huggingface.co/MediaTek-Research/Breeze-7B-FC-v1_0) | 7B | MediaTek Research | Apache 2.0 | ✅ | ✅ | +| [Gorilla-OpenFunctions-v2](https://huggingface.co/MediaTek-Research/Breeze-7B-FC-v1_0) | 7B | Gorilla LLM | Apache 2.0 | ✅ | ❌ | +| [GPT-3.5-Turbo-0125](https://openai.com) | | OpenAI | Proprietary| ✅ | ✅ | + +**Evaluate function calling on EN benchmark** + +We evaluate the performance of function calling on English with benchmark [Berkeley function-calling leaderboard](https://gorilla.cs.berkeley.edu/blogs/8_berkeley_function_calling_leaderboard.html). + +| Models | ↑ Overall | Irrelevance
Detection | AST/
Simple | AST/
Multiple | AST/
Parallel | AST/
Parallel-Multiple | Exec/
Simple | Exec/
Multiple | Exec/
Parallel | Exec/
Parallel-Multiple | +|-----------------------------------|----------|---------------------|------------|--------------|--------------|------------------------|--------------|---------------------|---------------------|-------------------------------| +| **Breeze-7B-FC-v1_0 (FC)** | 86.89 | 76.25 | 90.00 | 93.00 | 84.00 | 84.00 | 100.00 | 92.00 | 88.00 | 77.50 | +| Gorilla-OpenFunctions-v2 (FC) | 85.95 | 60.00 | 94.25 | 95.50 | 86.50 | 86.00 | 97.00 | 96.00 | 80.00 | 75.00 | +| GPT-3.5-Turbo-0125 (FC) | 72.77 | 4.58 | 87.75 | 90.50 | 88.50 | 82.50 | 91.00 | 82.00 | 78.00 | 52.50 | + + + +![](misc/radar_chart_en.png) + +**Evaluate function calling on ZHTW benchmark** + +We evaluate the performance of function calling on Traditional Chinese with benchmark [function-calling-leaderboard-for-zhtw](https://github.com/mtkresearch/function-calling-leaderboard-for-zhtw). + +| Models | ↑ Overall | Irrelevance
Detection | AST/
Simple | AST/
Multiple | AST/
Parallel | AST/
Parallel-Multiple | Exec/
Simple | Exec/
Multiple | Exec/
Parallel | Exec/
Parallel-Multiple | +|-----------------------------------|----------|---------------------|------------|--------------|--------------|------------------------|--------------|---------------------|---------------------|-------------------------------| +| **Breeze-7B-FC-v1_0 (FC)** | 78.18 | 72.50 | 82.00 | 86.00 | 76.50|67.00|88.00|88.00|80.00|60.00| +| Gorilla-OpenFunctions-v2 (FC) | 75.68 | 53.75 | 84.75 | 86.50 | 72.50 | 68.00 | 92.00 | 92.00 | 62.00 | 72.50 | +| GPT-3.5-Turbo-0125 (FC) | 66.15 | 7.50 | 83.75 | 83.50 | 73.00 | 65.50 | 88.00 | 84.00 | 72.00 | 40.00 | + + + +![](misc/radar_chart_zhtw.png) + + + **Evaluate instrustion following on EN benchmark** + +We evaluate the performance of instruction following on English with benchmark [MT-Bench](https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/README.md). + +| | Win | Tie | Lose | +|---|---|---|---| +| **Breeze-7B-FC-v1_0** *v.s.* Breeze-7B-Instruct-v1_0 | 29 (18.1%) | 55 (34.3%) | 76 (47.5%) | + + +**Evaluate instrustion following on ZHTW benchmark** + +We evaluate the performance of instruction following on Traditional Chinese with benchmark [MT-Bench-TC](https://github.com/mtkresearch/TCEval). + +| | Win | Tie | Lose | +|---|---|---|---| +| **Breeze-7B-FC-v1_0** *v.s.* Breeze-7B-Instruct-v1_0 | 35 (21.9%) | 73 (45.6%) | 52 (32.5%) | + + +## 👩‍💻 How to use + +**Demo with Kaggle Kernel** + +Start from clicking the "Copy & Edit" button on https://www.kaggle.com/code/ycckaggle/run-breeze-fc + +**Dependiency** + +Install `mtkresearch` package + +``` +pip install mtkresearch +``` + +**Hosting the model by VLLM** + +```python +from vllm import LLM, SamplingParams + +llm = LLM( + model='MediaTek-Research/Breeze-7B-FC-v1_0', + tensor_parallel_size=num_gpu, # number of gpus + gpu_memory_utilization=0.7, + dtype='half' +) + +turn_end_token_id = 61876 # <|im_end|> +params = SamplingParams( + temperature=0.01, + top_p=0.01, + max_tokens=4096, + repetition_penalty=1.1, + stop_token_ids=[turn_end_token_id] +) + +def _inference(prompt, llm, params): + return llm.generate(prompt, params)[0].outputs[0].text + +``` + +**Instruction following** + +```python +from mtkresearch.llm.prompt import MRPromptV2 + +sys_prompt = ('You are a helpful AI assistant built by MediaTek Research. ' + 'The user you are helping speaks Traditional Chinese and comes from Taiwan.') + +prompt_engine = MRPromptV2() + +conversations = [ + {"role": "system", "content": sys_prompt}, + {"role": "user", "content": "請問什麼是深度學習？"}, +] + +prompt = prompt_engine.get_prompt(conversations) + + +output_str = _inference(prompt, llm, params) +result = prompt_engine.parse_generated_str(output_str) + +print(result) +# {'role': 'assistant', +# 'content': '深度學習（Deep Learning）是一種機器學習方法，它模仿人類大腦的神經網路結構來 +# 處理複雜的數據和任務。在深度學習中，模型由多層人工神經元組成，每個神經元之間有 +# 權重連接，並通過非線性轉換進行計算。這些層與層之間的相互作用使模型能夠學習複雜 +# 的函數關係或模式，從而解決各種問題，如圖像識別、自然語言理解、語音辨識等。深度 +# 學習通常需要大量的數據和強大的計算能力，因此經常使用圖形處理器（GPU）或特殊的 +# 加速器來執行。'} +``` + +**Function Calling** + +```python +import json + +from mtkresearch.llm.prompt import MRPromptV2 + +functions = [ + { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } +] + +def fake_get_current_weather(location, unit=None): + return {'temperature': 30} + +mapping = { + 'get_current_weather': fake_get_current_weather +} + +prompt_engine = MRPromptV2() + +# stage 1: query +conversations = [ + {"role": "user", "content": "請問台北目前溫度是攝氏幾度？"}, +] + +prompt = prompt_engine.get_prompt(conversations, functions=functions) + +output_str = _inference(prompt, llm, params) +result = prompt_engine.parse_generated_str(output_str) + +print(result) +# {'role': 'assistant', +# 'tool_calls': [ +# {'id': 'call_U9bYCBRAbF639uUqfwehwSbw', 'type': 'function', +# 'function': {'name': 'get_current_weather', 'arguments': '{"location": "台北, 台灣", "unit": "celsius"}'}}]} + +# stage 2: execute called functions +conversations.append(result) + +tool_call = result['tool_calls'][0] +func_name = tool_call['function']['name'] +func = mapping[func_name] +arguments = json.loads(tool_call['function']['arguments']) +called_result = func(**arguments) + +# stage 3: put executed results +conversations.append( + { + 'role': 'tool', + 'tool_call_id': tool_call['id'], + 'name': func_name, + 'content': json.dumps(called_result) + } +) + +prompt = prompt_engine.get_prompt(conversations, functions=functions) + +output_str2 = _inference(prompt, llm, params) +result2 = prompt_engine.parse_generated_str(output_str2) +print(result2) +# {'role': 'assistant', 'content': '台北目前的溫度是攝氏30度'} +``` + +## Citation + +If you find this work is useful, please cite it with: + +``` +@article{chen2024enhancing, + title={Enhancing Function-Calling Capabilities in LLMs: Strategies for Prompt Formats, Data Integration, and Multilingual Translation}, + author={Chen, Yi-Chang and Hsu, Po-Chun and Hsu, Chan-Jan and Shiu, Da-shan}, + journal={arXiv preprint arXiv:2412.01130}, + year={2024}, + url={https://arxiv.org/abs/2412.01130} +} +``` diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..8d75884 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,10 @@ +{ + "": 61873, + "": 61874, + "<|answer|>": 61880, + "<|im_end|>": 61876, + "<|im_start|>": 61875, + "<|tool_call_begin|>": 61877, + "<|tool_call_end|>": 61878, + "<|use_tool|>": 61879 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..690a2c1 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "output_router_logits": true, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.41.1", + "use_cache": false, + "vocab_size": 61952 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "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..48cc84e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "transformers_version": "4.41.1" +} diff --git a/misc/radar_chart_en.png b/misc/radar_chart_en.png new file mode 100644 index 0000000..ca6d6fb Binary files /dev/null and b/misc/radar_chart_en.png differ diff --git a/misc/radar_chart_zhtw.png b/misc/radar_chart_zhtw.png new file mode 100644 index 0000000..ddcc091 Binary files /dev/null and b/misc/radar_chart_zhtw.png differ diff --git a/pytorch_model-00001-of-00004.bin b/pytorch_model-00001-of-00004.bin new file mode 100644 index 0000000..398e579 --- /dev/null +++ b/pytorch_model-00001-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e0caa896a6293544925c466cc9a6c02ddf9ff13f291f7e266250bbe8220949 +size 4953669456 diff --git a/pytorch_model-00002-of-00004.bin b/pytorch_model-00002-of-00004.bin new file mode 100644 index 0000000..2f2cc1d --- /dev/null +++ b/pytorch_model-00002-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aeba1d9f9f17c5c97999b2e6ea8baeea5f3f23fa9aa3086f4fd4104eb84dc3a +size 4915938762 diff --git a/pytorch_model-00003-of-00004.bin b/pytorch_model-00003-of-00004.bin new file mode 100644 index 0000000..bbd7326 --- /dev/null +++ b/pytorch_model-00003-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387307f1181d6decb3c5918a64375895982c3878b69926a0e786b7aafa767913 +size 4597178100 diff --git a/pytorch_model-00004-of-00004.bin b/pytorch_model-00004-of-00004.bin new file mode 100644 index 0000000..aefb061 --- /dev/null +++ b/pytorch_model-00004-of-00004.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5450a6cf1df6f4bd8294e42be347a3137d785f6a3c575471cb7206edfbe847a0 +size 507512197 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..606546a --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14974197760 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00004-of-00004.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin", + "model.norm.weight": "pytorch_model-00003-of-00004.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8dd4e26 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130 +size 911034 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..93e07cc --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,107 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61873": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61874": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "61875": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61876": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61877": { + "content": "<|tool_call_begin|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61878": { + "content": "<|tool_call_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61879": { + "content": "<|use_tool|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61880": { + "content": "<|answer|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}