mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-19 02:29:47 +00:00
9b211a45d6
The single-episode `segment_skills` method was missing `enable_thinking=False` in `apply_chat_template`, causing the model to output reasoning traces instead of JSON when the batch path fails and falls back to per-episode processing. Made-with: Cursor