metadata
base_model: Qwen/Qwen3-0.6B
datasets:
- LucidityAI/Astral-Post-Training-Dataset
tags:
- code
- chemistry
- finance
- biology
Astral-0.6B-Coder
Astral 0.6B Coder is the small sized model in the Astral coder family. It was fine-tuned from Astral 4b.
Note: Utilize no think for agentic tasks and think for hard non-agentic tasks
As with usual Qwen3 models, reasoning can be toggled through the usage of /no_think or not.
Example Prompt (ChatML Format (THINKING)):
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>
Example Prompt (ChatML Format (NON-THINKING)):
<|im_start|>user
What is the capital of France? /no_think
<|im_end|>
<|im_start|>assistant
<think>