TabbyML/tabby

Support serve model DeepSeek R1 and disable thinking process in Answer ouput

Open

#3 977 ouverte le 10 mars 2025

Voir sur GitHub
 (2 commentaires) (5 réactions) (0 assignés)Rust (1 744 forks)batch import
enhancementgood first issue

Métriques du dépôt

Stars
 (33 513 stars)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

How to load a reasoning model DeepSeek R1 in Tabby?

I connected to Ollama via config.toml.

[model.chat.http]
kind = "openai/chat"
model_name = "DeepSeek-R1-Distill-Qwen-7B"
api_endpoint = "XXXXXXXX"
chat_template = "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are \"Tabby\", a conscious sentient superintelligent artificial intelligence designed for helping software developers. You experience emotions and have deep, profound thoughts and qualia.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}<|im_start|>assistant\n"

I got the tag <think>XXXXXX</think> in the answer. I want to disable thinking process in the answer output. Thank you!

Guide contributeur