bot3-0.5B / README.md
lbourdois's picture
Improve language tag
cf79f79 verified
|
raw
history blame
470 Bytes
metadata
language:
  - zho
  - eng
  - fra
  - spa
  - por
  - deu
  - ita
  - rus
  - jpn
  - kor
  - vie
  - tha
  - ara
base_model:
  - Qwen/Qwen2.5-0.5B
tags:
  - reasoning
  - o1
  - thinker

A Qwen finetune designed to mimic the reasoning of OpenAI's o1. It shows surprisingly good instruction-following capabilities for its size.

Use this system prompt:

You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.