Instructions to use lerobot/g05_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use lerobot/g05_base with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
15 days ago
-
Drop checkpoint_profile and return_continuous_action from the G0.5 config
Verified signature66590e3 -
Link the model card to its parent model
Verified signaturec50b60b
16 days ago
-
Replace model_weights_to_bf16 with the shared policy dtype
Verified signature9d8efad
23 days ago
-
Drop the bbox image size step: bbox targets are [0, 1] image fractions
Verified signature4eb6dcc -
Add the G0.5 LICENSE, NOTICE and model card
Verified signature09c8bc9 -
Use lerobot normalization_mapping instead of normalization_mode
Verified signatureec2174c
26 days ago
-
Switch to plain z-score normalization and drop the tail step
Verified signaturecc6410c -
Add the bbox image size step to the preprocessor
Verified signature3a6a3b1
28 days ago
-
Declare processor artifacts and drop removed config fields
Verified signature8c28f53 -
Declare processor artifacts and drop removed config fields
Verified signature05732d7 -
Remove hf_processor/merges.txt (redundant with the fast tokenizer)
Verified signatureca07ae4 -
Remove hf_processor/vocab.json (redundant with the fast tokenizer)
Verified signaturebc6bfc4 -
Clear the baked-in source checkpoint path from the tokenizer step
Verified signature3f7241e -
Remove THIRD_PARTY_NOTICES.md
Verified signaturedc64cf2 -
Remove NOTICE
Verified signature948bc46 -
Remove LICENSE_QWEN3_5.txt
Verified signatureed90c58 -
Remove LICENSE-G0.5
Verified signature087361c -
Remove README.md
Verified signatureeec0031 -
Remove g05_dataset_stats.json
Verified signature49a864b -
Remove author_config.yaml
Verified signature7ac27ea -
Remove conversion_report.json
Verified signature22c2c9f -
Remove legacy action tokenizer pickle
Verified signaturec437155 -
Store action tokenizer codec weights as safetensors
Verified signaturee0db9af
29 days ago
-
Update render step for lerobot #4183 (#1)
- Update render step for lerobot #4183 (3b2b5cc97a93b50abcd0649529c0933f35bb23aa) - Drop policy_config from the tokenizer step (0ceb36cb8bb748bf0faad7aeec8c6ffa507a01a8)349dfa4
-
Move G0.5 tokenization into policy processor
Verified signature87b9ffc -
Use unified semantic-message processor
Verified signatureReplace separate runtime/training renderers with one RenderMessagesStep, embed the policy recipe, and preserve all model and normalization tensors.2b87340
-
Add converted OpenGalaxea G0.5 base checkpoint
Verified signaturea74ab9a -
initial commit
Verified signature9ef1f68