2 items • Updated
Astral-4B-Coder
Astral 4B is the largest sized model in the Astral coder family. It was fine-tuned from Astral 4b on LucidityAI/Astral-Post-Training-Dataset.
Use /no_think for agentic tasks, use thinking for non-agentic coding 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>
- Downloads last month
- 3
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
