admin

admin synced commits to refs/heads/feat/audio_dataset at admin/lerobot from mirror 2026-04-29 16:59:41 +00:00

e6e54391bd fix(missing method): adding missing add_microphones_recordings method in LeRobotDataset

a201b33d20 chore(typos): fixing uncaught typos

Compare 2 commits »

admin synced commits to refs/heads/main at admin/lerobot from mirror 2026-04-29 16:59:41 +00:00

b5f65e5332 Expose sarm package API and ship reward model card template (#3477)

cd6b43ea7a fix(train): migrate legacy RA-BC fields in train config loading (#3480)

2236bbe7a3 fix(rollout): propagate policy-specific CLI config paramaters (#3483)

Compare 3 commits »

admin synced commits to refs/heads/auto/update-uv-lock at admin/lerobot from mirror 2026-04-29 08:49:43 +00:00

8669e71b89 chore(dependencies): update uv.lock

cb0a944941 refactor(datasets): replace untyped dict with typed DatasetInfo dataclass (#3472)

8a3d64033f Reward models refactor (#3142)

03ee50e08f chore(ci): bump docs workflows (#3476)

Compare 4 commits »

admin synced and deleted reference refs/heads/chore/info-json-typed-dataclass at admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

admin synced commits to refs/heads/feat/leader_activate_teleop at admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

5c444302c1 feat(so_follower): synchronize goal position with present position to prevent positional error during torque re-enablement

admin synced new reference refs/heads/fix/reward_models_refactoring to admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

admin synced commits to refs/heads/fix/reward_models_refactoring at admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

admin synced commits to refs/heads/main at admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

cb0a944941 refactor(datasets): replace untyped dict with typed DatasetInfo dataclass (#3472)

admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-04-29 00:39:41 +00:00

72d0fc0dce refactor(annotate): drop HF Inference Providers code path

3c6a6b39a2 feat(annotate): --vlm.push_to_hub uploads the annotated dataset

39f6167fa3 feat(annotate): parallelize episodes within each module phase

caef184c82 fix(annotate): probe /v1/models for spawn-helper readiness

7bbf5777a2 fix(annotate): lock-protect per-line writes for parallel server streams

Compare 18 commits »

admin synced and deleted reference refs/heads/refactor/reward-models at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

admin synced commits to refs/heads/chore/info-json-typed-dataclass at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

943295eba6 use consistantly int for data and video_files_size_in_mb

fb8fc1a7b6 fix crop dataset roi type mismatch

16b5010b34 refactoring the last few old fieds

de05a00dd0 update docstring inside DatasetInfo.from_dict()

7fb32168dd fix pre-commit

Compare 8 commits »

admin synced new reference refs/heads/feat/leader-arm-intervention-pr2596 to admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

admin synced commits to refs/heads/feat/leader-arm-intervention-pr2596 at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

aded6214ab fix(annotate): detect server ready via stdout banner, not /v1/models polls

e70277ba3e fix(annotate): visible auto_serve via stdout prints + live server log stream

4930338c52 fix(annotate): auto_serve defaults to True; probe before spawning

55879e4fb4 feat(annotate): auto_serve mode spawns and tears down inference server

0b2f0d1d6a feat(annotate): video_url block for openai backend

Compare 14 commits »

admin synced commits to refs/heads/main at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

8a3d64033f Reward models refactor (#3142)

03ee50e08f chore(ci): bump docs workflows (#3476)

Compare 2 commits »

admin synced commits to refs/heads/user/khalil-meftah/2026-02-16-rl-stack-refactor at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

6ed80f5a59 Merge remote-tracking branch 'origin/main' into user/khalil-meftah/2026-02-16-rl-stack-refactor

ef6b3b5b0f refactor: simplify docstrings for clarity and conciseness across multiple files

ca87ccd941 feat(rollout): decouple policy deployment from data recording with new lerobot-rollout CLI (#3413)

77352c495c chore(dependencies): update uv.lock (#3437)

05a5223885 fix(pi): avoid peak RAM in PiGemma construction by freeing replaced submodules (#3454)

Compare 37 commits »

admin synced new reference refs/heads/feat/leader_activate_teleop to admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

admin synced commits to refs/heads/feat/leader_activate_teleop at admin/lerobot from mirror 2026-04-28 16:29:42 +00:00

admin synced commits to refs/heads/feat/language-annotation-pipeline at admin/lerobot from mirror 2026-04-28 08:28:50 +00:00

a81e23b0e9 fix(annotate): pass trust_remote_code=True to HF auto-classes

admin synced new reference refs/heads/auto/update-uv-lock to admin/lerobot from mirror 2026-04-28 08:28:50 +00:00