📌 📄 内容摘要:
xscr 在 unsloth Tutorial: How to Run QwQ-32B effectively 中发帖
介绍了如何有效运行QwQ-32B模型，包括推荐设置、问题修复及使用教程。
Tutorial: How to Run QwQ-32B effectively
Official Recommended Settings
According to Qwen, these are the recommended settings for inference:
Temperature of 0.6
Top_K of 40 (or 20 to 40)
Min_P of 0.02 (optional, but works well, llama.cpp default is 0.1)
Top_P of 0.95
Repetition Penalty of 1.0. (1.0 means disabled in llama.cpp and transformers)
Chat template:...
────────── 链接信息 ──────────
🔗 论坛链接: linux.do
📎 访问地址: https://linux.do/t/topic/480113/1
─────────────────────────────
📢 来源：LINUX DO
