mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-28 06:59:44 +00:00
Pepijn
1ff10b935c
Resolves conflicts from 66 commits on the base branch: * pyproject.toml — keep base's transformers>=5.4.0,<5.6.0; add the sentencepiece-dep entry pi052 (FAST action tokenizer) needs. * policies/__init__.py — keep pi052 export; drop the RewardClassifierConfig export that base removed. * policies/factory.py — docstring list resolution (keep pi052; drop reward_classifier, removed by base). * annotations/steerable_pipeline/executor.py — adopt base's renamed _ensure_annotation_metadata_in_info (it already advertises the say tool); drop pi052's older _ensure_tools_in_info call. * configs/train.py — keep pi052's vqa_target_fraction; adopt base's SampleWeightingConfig (legacy RA-BC inline params already covered by the migration shim base added). * scripts/lerobot_train.py — merge pi052's per-policy processor rebuild + dataset_repo_id pass-through with base's active_cfg / is_reward_model_training tightening, and re-route vqa-weighted sampler to active_cfg.drop_n_last_frames. * datasets/language_render.py — adopt base's _select_one + timestamp tolerance (drops pi052's stale _select_latest / per-style sort_key). * tests — adopt base's parametrized per-camera blend + tolerance test; drop pi052 tests that overlap with base's tighter rewrites; keep pi052's flow-only / VQA-blend coverage; add a test_canonical_recipe_loads check on subtask_mem_vqa_speech.yaml. * policies/pi052/processor_pi052.py — import RenderMessagesStep directly from render_messages_processor (base intentionally dropped it from lerobot.processor's re-exports). * uv.lock — regenerated cleanly from base + pi052's pocket-tts / beartype. All 67 touched tests pass (30 pi052 + 37 recipe / language-render / pipeline / render-messages). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
97 lines
3.7 KiB
Python
97 lines
3.7 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. discovers the dataset's canonical subtask + memory vocabulary
|
|
from the first 3 sample episodes (phase 0),
|
|
4. runs the plan / interjections / vqa modules across the dataset
|
|
(subtasks + memory are constrained to the canonical vocabulary),
|
|
5. 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=imstevenpmwork/super_poulain_draft "
|
|
"--dest_repo_id=pepijn223/super_poulain_vocab "
|
|
"--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.wrist "
|
|
<<<<<<< HEAD:examples/annotation/run_hf_job.py
|
|
"--module_1.frames_per_second=1.0 "
|
|
"--module_1.use_video_url=true "
|
|
"--module_1.use_video_url_fps=1.0 "
|
|
"--module_1.derive_task_from_video=always "
|
|
"--module_1.n_task_rephrasings=30 "
|
|
"--module_2.max_interjections_per_episode=6 "
|
|
"--module_3.K=3 "
|
|
"--module_3.vqa_emission_hz=1.0 "
|
|
"--push_to_hub=pepijn223/super_poulain_full_tool3"
|
|
=======
|
|
# Phase 0 — canonical vocabulary discovery from the first N sample
|
|
# episodes. The VLM picks the right number of subtask + memory
|
|
# entries itself from what it sees; the resulting
|
|
# meta/canonical_vocabulary.json constrains every subtask + memory
|
|
# string to a small repeatable target distribution.
|
|
"--vocabulary.sample_episodes=3 "
|
|
# 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.n_task_rephrasings=30 "
|
|
# Phase 2 — interjections + speech.
|
|
"--interjections.max_interjections_per_episode=6 "
|
|
# Phase 4 — general VQA.
|
|
"--vqa.K=3 "
|
|
"--vqa.vqa_emission_hz=1.0"
|
|
>>>>>>> origin/feat/language-annotation-pipeline:examples/annotations/run_hf_job.py
|
|
)
|
|
|
|
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}")
|