metadata
library_name: transformers
license: mit
datasets:
- PrimeIntellect/Reverse-Text-SFT
base_model:
- PrimeIntellect/Qwen3-0.6B
Qwen3-0.6B-Reverse-Text-SFT
A debug model fine-tuned on 128 token context on PrimeIntellect/Reverse-Text-SFT. To be used as warmed up model to RL in vf-reverse-text.
Created with this training command from prime-rl (commit hash: ed25704)
uv run sft @ configs/reverse_text/sft.toml --ckpt