Phi-4-reasoning

> [!IMPORTANT] > To fully take advantage of the model's capabilities, inference must use `temperature=0.8`, `top_k=50`, `top_p=0.95`, and `do_sample=True`. For more complex queries, set `max_new_tokens=32768` to allow for longer chain-of-thought (CoT). Given the nature of the training data, **always use** ChatML template with the **following system prompt** for inference: *Phi-4-reasoning is also supported out-of-the-box by Ollama, llama.cpp, and any Phi-4 compatible framework.*

번역 준비 중입니다. 원문을 표시합니다.