admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-22 03:59:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: disable thinking mode in Qwen35VL single-episode fallback path

Browse Source 
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
This commit is contained in:
Pepijn
2026-03-30 15:31:18 +02:00
parent a6387da464
commit 9b211a45d6
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/data_processing/data_annotations/vlm_annotations.py
+3 -1
View File
@@ -495,7 +495,9 @@ class Qwen35VL(BaseVLM):
}, },
] ]
text = self.processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) text = self.processor.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
)
image_inputs, video_inputs = self.process_vision_info(messages) image_inputs, video_inputs = self.process_vision_info(messages)
inputs = self.processor( inputs = self.processor(
text=[text], text=[text],