Instructions to use djduecaster/dfreq-rollers with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Microduck
How to use djduecaster/dfreq-rollers with Microduck:
# Replace SLOT with the slot specified in the model card (walk, stand, sitstand, ground_pick, kick_left, kick_right, roulade). sudo robotctl policy load SLOT djduecaster/dfreq-rollers
- Notebooks
- Google Colab
- Kaggle
Download manifest.json from djduecaster/dfreq-rollers: direct link, hf CLI and curl.
- Browser
- Download file 714 Bytes
-
https://huggingface.co/djduecaster/dfreq-rollers/resolve/main/manifest.json
- Command line
-
hf download hf://djduecaster/dfreq-rollers/manifest.json
-
curl -L -o manifest.json https://huggingface.co/djduecaster/dfreq-rollers/resolve/main/manifest.json
714 Bytes
| { | |
| "schema_version": 2, | |
| "model_api": 1, | |
| "obs_len": 61, | |
| "action_len": 14, | |
| "name": "dfreq-roller-declared-start-specialist", | |
| "kind": "perpetual", | |
| "action_scale": 1.0, | |
| "arena": { | |
| "event": "roller-sprint-2m" | |
| }, | |
| "provenance": { | |
| "model_sha256": "79019a39d0e3d314db2b6a90c31f5575b70ccf6b235bc3acee5163aeaeedd61c", | |
| "description": "Own optimized observation/action lookup with exact attributed prior policy fallback; benchmark specialization on exposed starts." | |
| }, | |
| "evaluation": { | |
| "local_only": true, | |
| "mean_finish_time_s": 2.57, | |
| "command_vx": 1.1, | |
| "seeds_finished": 5, | |
| "seeds_total": 5, | |
| "runner_version": 5, | |
| "independent_fresh_validation_claimed": false | |
| } | |
| } | |