Astral-4B-Preview / README.md
sd-inf's picture
Update README.md
3df9364 verified
---
license: apache-2.0
base_model: Qwen/Qwen3-4b-thinking-2507
tags:
- reasoning
- code
- inference
- chat
- multimodal (if applicable)
library_name: transformers
datasets:
- nvidia/AceReason-1.1-SFT
---
# Astral-4B-Preview
Astral-4B is a specialized reasoning-focused language model developed as part of the Astral series, designed to deliver high-fidelity, step-by-step reasoning with configurable depth. Built upon the Qwen3-4b-thinking-2507 foundation, this variant has been fine-tuned on the `nvidia/AceReason-1.1-SFT` dataset to enhance logical coherence, problem-solving capability, and structured thinking.
This model is currently in **preview** and intended for research, evaluation, and development use. Feedback is encouraged to guide future iterations.
---
## Usage Instructions
To invoke the model correctly, include a **reasoning-level indicator** in the system prompt using the `Reasoning-level:` directive. The available levels are:
| Level | Behavior |
|----------|--------|
| `none` | No reasoning trace generated, direct response only. |
| `low` | Minimal internal reasoning |
| `medium` | Creates a reasoning trace thats not too long nor too short |
| `high` | Second highest reasoning depth |
| `ultra` | Maximum depth reasoning |
> **Note**: The absence of a valid reasoning level will result in undefined behavior. Always specify one.
### Example Prompt (ChatML Format):
```xml
<|im_start|>system
Reasoning-level: high
<|im_end|>
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>
```
---
## Important Notes
- This is a **preview release**. Performance may vary across edge cases or non-standard inputs.
- For production applications, please wait for the official release.
---