TabbyML/tabby

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

Open

#3,977 opened on Mar 10, 2025

View on GitHub
 (2 comments) (5 reactions) (0 assignees)Rust (33,513 stars) (1,744 forks)batch import
enhancementgood first issue

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!

Contributor guide

Tech stack
rust
Domain
backendapiai
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Tabby configuration (toml)Understanding of model output formatBasic Rust knowledgeAPI integration concepts
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40
Research direction
Investigate how Tabby processes model responses, focusing on the Ollama integration and chat template handling. Look for existing filtering mechanisms for special tokens like `<think>`. Check the configuration options for model.chat.http. Consider adding a post processing step to strip `<think>...</think>` tags. Relevant files may include `tabby/src/...` for model serving and `chat template.rs` or similar.