Safetensors
English
qwen3
Astral-1.5-4B / README.md
sd-inf's picture
Update README.md
8cf2b70 verified
---
datasets:
- LucidityAI/Astral-1.5-Post-Training-Dataset-SFT
- LucidityAI/Astral-1.5-Post-Training-Dataset-CRLFT
language:
- en
---
# Astral 1.5 4B
Astral 1.5 4B is a updated version of the Astral 4B model, trained for STEM tasks and agentic usage.
The model was trained on our Astral-1.5-Post-Training-SFT and Astral-1.5-Post-Training-CRLFT datasets.
## Comparisons
When asked for a TailwindCSS HTML page for a photo editing software models gave the following (zero-shot responses):
Qwen3 4B 2507 Thinking (8101 tokens used)
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/QdZB10AELDKVN-N06hrvZ.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/wKgkEt9iUpCJFdnBIZ_Kr.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/MiYP2g38wdJjQZyDHSRtz.png" width="300" height="300" />
Astral 1.5 4B (6088 tokens used)
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/zq-L7jDRhKAcuYQVn_KeQ.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/U9ZOEYv0EhsOxof1cTenC.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/4dzf12UFlQRGF_YTNasMc.png" width="300" height="300" />
GPT-5.2
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/RI-hntpKSYXmZiPXN48q_.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/Kci7Xs9dFDz93P9ouxhLq.png" width="300" height="300" />
<img src="https://cdn-uploads.huggingface.co/production/uploads/650707344a8839a8bd85ae2f/FstCN0MeL7I6lFzgkKfVK.png" width="300" height="300" />
## Usage
You may utilize the following chat template to do regular chat completions with the model:
```
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>
CORRECT:
The
```
or to use it as an agent, you must prefill `<think>Agent mode is on</think>` like so:
```
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>assistant
<think>
Agent mode is on
</think>
```