Astral-1.5-4B-Preview-fixed

Note: This is on a different repo than the original preview, as for there was an issue merging the original model, leading it it being highly unreliable.

• low: Generates a smaller reasoning trace
• medium: Generates a decent sized reasoning trace:
• high: Generates a generally unrestricted in size trace
• agent: Genreates no reasoning trace. Intended for agentic use.

<|im_start|>reasoning_level
medium
<|im_end|>
<|im_start|>user
What is the capital of France?
<|im_end|>
<|im_start|>