From 81b905870571a969886638ed6179b80889cb8168 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Tue, 29 Apr 2025 00:07:11 +0800 Subject: [PATCH] Update README.md --- README.md | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index 4adec64..61e8e40 100644 --- a/README.md +++ b/README.md @@ -83,21 +83,24 @@ print("thinking content:", thinking_content) print("content:", content) ``` -For deployment, you can use `vllm>=0.8.5` or `sglang>=0.4.5.post2` to create an OpenAI-compatible API endpoint: +For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or to create an OpenAI-compatible API endpoint: +- SGLang: + ```shell + python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser qwen3 + ``` - vLLM: ```shell vllm serve Qwen/Qwen3-0.6B --enable-reasoning --reasoning-parser deepseek_r1 ``` -- SGLang: - ```shell - python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser deepseek-r1 - ``` + +For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3. + ## Switching Between Thinking and Non-Thinking Mode > [!TIP] -> The `enable_thinking` switch is also available in APIs created by vLLM and SGLang. -> Please refer to our documentation for [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) and [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) users. +> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM. +> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users. ### `enable_thinking=True` @@ -117,7 +120,6 @@ In this mode, the model will generate think content wrapped in a `... [!NOTE] > For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section. - ### `enable_thinking=False` We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.