commit 7ab3e25db8ce2fff76f3201c20f11352a5de1405 Author: ModelHub XC Date: Sun May 31 12:45:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Eslzzyl/Qwen3-4B-Instruct-2507-AWQ Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fa4bd8f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..0a533db --- /dev/null +++ b/README.md @@ -0,0 +1,221 @@ +--- +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +pipeline_tag: text-generation +base_model: +- Qwen/Qwen3-4B-Instruct-2507 +--- + +# Qwen3-4B-Instruct-2507-AWQ + +## Method + +Quantized using [casper-hansen/AutoAWQ](https://github.com/casper-hansen/AutoAWQ), [swift/Chinese-Qwen3-235B-2507-Distill-data-110k-SFT](https://modelscope.cn/datasets/swift/Chinese-Qwen3-235B-2507-Distill-data-110k-SFT) + +This model is quantized using AutoAWQ and can be deployed normally in [lmdeploy](https://github.com/InternLM/lmdeploy). This model is compatible with NVIDIA Turing GPUs (SM 75). + +# Qwen3-4B-Instruct-2507 + + Chat + + +## Highlights + +We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements: + +- **Significant improvements** in general capabilities, including **instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage**. +- **Substantial gains** in long-tail knowledge coverage across **multiple languages**. +- **Markedly better alignment** with user preferences in **subjective and open-ended tasks**, enabling more helpful responses and higher-quality text generation. +- **Enhanced capabilities** in **256K long-context understanding**. + +![image/jpeg](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-2507/Qwen3-4B-Instruct.001.jpeg) + +## Model Overview + +**Qwen3-4B-Instruct-2507** has the following features: +- Type: Causal Language Models +- Training Stage: Pretraining & Post-training +- Number of Parameters: 4.0B +- Number of Paramaters (Non-Embedding): 3.6B +- Number of Layers: 36 +- Number of Attention Heads (GQA): 32 for Q and 8 for KV +- Context Length: **262,144 natively**. + +**NOTE: This model supports only non-thinking mode and does not generate ```` blocks in its output. Meanwhile, specifying `enable_thinking=False` is no longer required.** + +For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/). + + +## Performance + +| | GPT-4.1-nano-2025-04-14 | Qwen3-30B-A3B Non-Thinking | Qwen3-4B Non-Thinking | Qwen3-4B-Instruct-2507 | +|--- | --- | --- | --- | --- | +| **Knowledge** | | | | +| MMLU-Pro | 62.8 | 69.1 | 58.0 | **69.6** | +| MMLU-Redux | 80.2 | 84.1 | 77.3 | **84.2** | +| GPQA | 50.3 | 54.8 | 41.7 | **62.0** | +| SuperGPQA | 32.2 | 42.2 | 32.0 | **42.8** | +| **Reasoning** | | | | +| AIME25 | 22.7 | 21.6 | 19.1 | **47.4** | +| HMMT25 | 9.7 | 12.0 | 12.1 | **31.0** | +| ZebraLogic | 14.8 | 33.2 | 35.2 | **80.2** | +| LiveBench 20241125 | 41.5 | 59.4 | 48.4 | **63.0** | +| **Coding** | | | | +| LiveCodeBench v6 (25.02-25.05) | 31.5 | 29.0 | 26.4 | **35.1** | +| MultiPL-E | 76.3 | 74.6 | 66.6 | **76.8** | +| Aider-Polyglot | 9.8 | **24.4** | 13.8 | 12.9 | +| **Alignment** | | | | +| IFEval | 74.5 | **83.7** | 81.2 | 83.4 | +| Arena-Hard v2* | 15.9 | 24.8 | 9.5 | **43.4** | +| Creative Writing v3 | 72.7 | 68.1 | 53.6 | **83.5** | +| WritingBench | 66.9 | 72.2 | 68.5 | **83.4** | +| **Agent** | | | | +| BFCL-v3 | 53.0 | 58.6 | 57.6 | **61.9** | +| TAU1-Retail | 23.5 | 38.3 | 24.3 | **48.7** | +| TAU1-Airline | 14.0 | 18.0 | 16.0 | **32.0** | +| TAU2-Retail | - | 31.6 | 28.1 | **40.4** | +| TAU2-Airline | - | 18.0 | 12.0 | **24.0** | +| TAU2-Telecom | - | **18.4** | 17.5 | 13.2 | +| **Multilingualism** | | | | +| MultiIF | 60.7 | **70.8** | 61.3 | 69.0 | +| MMLU-ProX | 56.2 | **65.1** | 49.6 | 61.6 | +| INCLUDE | 58.6 | **67.8** | 53.8 | 60.1 | +| PolyMATH | 15.6 | 23.3 | 16.6 | **31.1** | + +*: For reproducibility, we report the win rates evaluated by GPT-4.1. + + +## Quickstart + +The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`. + +With `transformers<4.51.0`, you will encounter the following error: +``` +KeyError: 'qwen3' +``` + +The following contains a code snippet illustrating how to use the model generate content based on given inputs. +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_name = "Qwen/Qwen3-4B-Instruct-2507" + +# load the tokenizer and the model +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype="auto", + device_map="auto" +) + +# prepare the model input +prompt = "Give me a short introduction to large language model." +messages = [ + {"role": "user", "content": prompt} +] +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +# conduct text completion +generated_ids = model.generate( + **model_inputs, + max_new_tokens=16384 +) +output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() + +content = tokenizer.decode(output_ids, skip_special_tokens=True) + +print("content:", content) +``` + +For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint: +- SGLang: + ```shell + python -m sglang.launch_server --model-path Qwen/Qwen3-4B-Instruct-2507 --context-length 262144 + ``` +- vLLM: + ```shell + vllm serve Qwen/Qwen3-4B-Instruct-2507 --max-model-len 262144 + ``` + +**Note: If you encounter out-of-memory (OOM) issues, consider reducing the context length to a shorter value, such as `32,768`.** + +For local use, applications such as Ollama, LMStudio, MLX-LM, llama.cpp, and KTransformers have also supported Qwen3. + +## Agentic Use + +Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity. + +To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself. +```python +from qwen_agent.agents import Assistant + +# Define LLM +llm_cfg = { + 'model': 'Qwen3-4B-Instruct-2507', + + # Use a custom endpoint compatible with OpenAI API: + 'model_server': 'http://localhost:8000/v1', # api_base + 'api_key': 'EMPTY', +} + +# Define Tools +tools = [ + {'mcpServers': { # You can specify the MCP configuration file + 'time': { + 'command': 'uvx', + 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai'] + }, + "fetch": { + "command": "uvx", + "args": ["mcp-server-fetch"] + } + } + }, + 'code_interpreter', # Built-in tools +] + +# Define Agent +bot = Assistant(llm=llm_cfg, function_list=tools) + +# Streaming generation +messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}] +for responses in bot.run(messages=messages): + pass +print(responses) +``` + +## Best Practices + +To achieve optimal performance, we recommend the following settings: + +1. **Sampling Parameters**: + - We suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. + - For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. + +2. **Adequate Output Length**: We recommend using an output length of 16,384 tokens for most queries, which is adequate for instruct models. + +3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking. + - **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt. + - **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`." + +### Citation + +If you find our work helpful, feel free to give us a cite. + +``` +@misc{qwen3technicalreport, + title={Qwen3 Technical Report}, + author={Qwen Team}, + year={2025}, + eprint={2505.09388}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2505.09388}, +} +``` \ 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..bf8c9ff --- /dev/null +++ b/config.json @@ -0,0 +1,38 @@ +{ + "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": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "quantization_config": { + "bits": 4, + "group_size": 128, + "modules_to_not_convert": null, + "quant_method": "awq", + "version": "gemm", + "zero_point": true + }, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..78f8477 --- /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": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.51.3" +} 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.safetensors b/model.safetensors new file mode 100644 index 0000000..7667503 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f856bff8f3841e9d7fe988f9cac47d4de3604530e70096ddf6b7a9b607145ea +size 2666027672 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..0327ad8 --- /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 message.content is string 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.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.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 {{- content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "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