mirror of
https://github.com/huggingface/lerobot.git
synced 2026-07-13 21:11:59 +00:00
Pepijn
98a519e7f2
VideoFrameProvider derived its default camera and camera list from meta.camera_keys, which mixes image- and video-stored cameras. The clip/decode paths read videos/<key>/from_timestamp, which only exists for video keys, so an image-stored camera sorted first (e.g. observation.images.wrist) crashed the plan phase with a KeyError. Restrict the list and default to meta.video_keys. Add a regression test and point the example job at the dataset's actual video camera. Skip bandit B607 (ffmpeg/git are intentionally resolved via PATH). Co-authored-by: Cursor <cursoragent@cursor.com>
79 lines
2.8 KiB
Python
79 lines
2.8 KiB
Python
#!/usr/bin/env python
|
|
"""Launch ``lerobot-annotate`` on a Hugging Face job (vllm + Qwen3.6 MoE).
|
|
|
|
Spawns one ``h200x2`` job that:
|
|
|
|
1. installs this branch of ``lerobot`` plus the annotation extras,
|
|
2. boots two vllm servers (one per GPU) with Qwen3.6-35B-A3B-FP8,
|
|
3. runs the plan / interjections / vqa modules across the dataset
|
|
in free-form mode (each episode generates its own subtasks +
|
|
memory),
|
|
4. uploads the annotated dataset to ``--dest_repo_id`` (when set)
|
|
or back to ``--repo_id``.
|
|
|
|
Usage:
|
|
|
|
HF_TOKEN=hf_... uv run python examples/annotations/run_hf_job.py
|
|
|
|
Adjust ``CMD`` below to point at your own dataset / target hub repo.
|
|
"""
|
|
|
|
import os
|
|
|
|
from huggingface_hub import get_token, run_job
|
|
|
|
token = os.environ.get("HF_TOKEN") or get_token()
|
|
if not token:
|
|
raise RuntimeError("No HF token. Run `huggingface-cli login` or `export HF_TOKEN=hf_...`")
|
|
|
|
CMD = (
|
|
"apt-get update -qq && apt-get install -y -qq git ffmpeg && "
|
|
"pip install --no-deps "
|
|
"'lerobot @ git+https://github.com/huggingface/lerobot.git@feat/language-annotation-pipeline' && "
|
|
"pip install --upgrade-strategy only-if-needed "
|
|
"datasets pyarrow av jsonlines draccus gymnasium torchcodec mergedeep pyyaml-include toml typing-inspect "
|
|
"openai && "
|
|
"export VLLM_MEMORY_PROFILER_ESTIMATE_CUDAGRAPHS=0 && "
|
|
"export VLLM_VIDEO_BACKEND=pyav && "
|
|
"lerobot-annotate "
|
|
"--repo_id=pepijn223/robocasa_smoke_2atomic_v3 "
|
|
"--dest_repo_id=pepijn223/robocasa_smoke_2atomic_v3_ann "
|
|
"--push_to_hub=true "
|
|
"--vlm.backend=openai "
|
|
"--vlm.model_id=Qwen/Qwen3.6-35B-A3B-FP8 "
|
|
"--vlm.parallel_servers=2 "
|
|
"--vlm.num_gpus=2 "
|
|
'--vlm.serve_command="vllm serve Qwen/Qwen3.6-35B-A3B-FP8 '
|
|
"--tensor-parallel-size 1 --max-model-len 32768 "
|
|
'--gpu-memory-utilization 0.8 --uvicorn-log-level warning --port {port}" '
|
|
"--vlm.serve_ready_timeout_s=1800 "
|
|
"--vlm.client_concurrency=128 "
|
|
"--vlm.max_new_tokens=512 "
|
|
"--vlm.temperature=0.7 "
|
|
"--executor.episode_parallelism=16 "
|
|
"--vlm.chat_template_kwargs='{\"enable_thinking\": false}' "
|
|
"--vlm.camera_key=observation.images.robot0_agentview_right "
|
|
# Phase 1 — plan module (subtasks + plan + memory + task_aug).
|
|
"--plan.frames_per_second=1.0 "
|
|
"--plan.use_video_url=true "
|
|
"--plan.use_video_url_fps=1.0 "
|
|
"--plan.derive_task_from_video=always "
|
|
"--plan.task_aug_axes.enabled=true "
|
|
"--plan.action_records.enabled=true "
|
|
# Phase 2 — interjections + speech.
|
|
"--interjections.max_interjections_per_episode=6 "
|
|
# Phase 4 — general VQA.
|
|
"--vqa.K=1 "
|
|
"--vqa.vqa_emission_hz=1.0"
|
|
)
|
|
|
|
job = run_job(
|
|
image="vllm/vllm-openai:latest",
|
|
command=["bash", "-c", CMD],
|
|
flavor="h200x2",
|
|
secrets={"HF_TOKEN": token},
|
|
timeout="2h",
|
|
)
|
|
print(f"Job URL: {job.url}")
|
|
print(f"Job ID: {job.id}")
|