Spaces:

zjunlp
/

lab-vla

Running on Zero

App Files Files Community

869 kB

Ctrl+K

Ctrl+K

1 contributor

History: 8 commits

multimodalart's picture

multimodalart HF Staff

Fix NaN state input on gr.Examples click; use gr.JSON output with rounded values

7de5fac verified 19 days ago

examples
Upload folder using huggingface_hub 19 days ago
src
Fix Qwen3VL attribute path: self.vlm.visual/.language_model -> self.vlm.model.visual/.language_model (transformers 4.57.6+ nests these under .model) 19 days ago
.gitattributes

1.52 kB
initial commit 19 days ago
README.md

1.55 kB
Upload folder using huggingface_hub 19 days ago
app.py

17.2 kB
Fix NaN state input on gr.Examples click; use gr.JSON output with rounded values 19 days ago
labsim_transforms.py

7.67 kB
Upload folder using huggingface_hub 19 days ago
labvla_schema.json

568 Bytes
Upload folder using huggingface_hub 19 days ago
requirements.txt

302 Bytes
Pin transformers==4.57.6 (matches upstream LabVLA's exact tested env); unbounded >=4.57.0 was resolving to transformers 5.x, which changed Qwen3VLVisionModel.forward() to return a 3-field ModelOutput instead of a 2-tuple, breaking image_embs, _ = self.vlm.model.visual(...) unpacking 19 days ago