File size: 759 Bytes
560c2e0 5caf02f 524a664 5caf02f 560c2e0 5caf02f 560c2e0 5caf02f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 |
---
base_model: LucidityAI/Astral-4B
datasets:
- LucidityAI/Astral-Post-Training-Dataset
tags:
- code
---
# 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)):
```xml
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>
```
### Example Prompt (ChatML Format (NON-THINKING)):
```xml
<|im_start|>user
What is the capital of France? /no_think
<|im_end|>
<|im_start|>assistant
<think>
``` |