mirror of
https://github.com/huggingface/lerobot.git
synced 2026-06-02 20:01:25 +00:00
5dbf0fac5f
Drops the optional Phase 0 vocabulary-discovery feature entirely.
With the new structured action records (Phase 1a + 1b) providing
cross-episode consistency via the deterministic template renderer,
the older vocabulary-constraint path is redundant and adds a second
constraint mechanism that wasn't well-validated in practice.
Removed:
* src/lerobot/annotations/steerable_pipeline/vocabulary.py
(Vocabulary dataclass + VocabularyDiscoveryModule + load_/
save_vocabulary helpers; canonical_vocabulary.json on-disk format)
* src/lerobot/annotations/steerable_pipeline/prompts/module_0_vocabulary.txt
(Phase 0 VLM prompt)
* tests/annotations/test_vocabulary.py
Pruned wiring across:
* config.py: VocabularyConfig dataclass + AnnotationPipelineConfig.
vocabulary field
* executor.py: vocabulary attribute on Executor + _run_vocabulary_
phase method + Phase 0 phases.append call in run()
* modules/plan_subtasks_memory.py: Vocabulary import + vocabulary
attribute + _subtask_vocabulary_block / _memory_vocabulary_block
helpers + _canonicalize_subtask / _normalize / _invalid_subtasks
/ _build_subtask_retry_message methods + vocabulary-gated retry
path in _generate_subtasks + empty-episode warning + _NORMALIZE_
STRIP_TOKENS constant
* prompts/module_1_subtasks.txt: {vocabulary_block} placeholder
* prompts/module_1_memory.txt: {vocabulary_block} placeholder
* __init__.py: Vocabulary / VocabularyDiscoveryModule / load_
vocabulary / save_vocabulary / vocabulary_path / VOCABULARY_
FILENAME re-exports
* scripts/lerobot_annotate.py: VocabularyDiscoveryModule import +
instantiation + executor argument
* examples/annotations/run_hf_job.py: --vocabulary.enabled=false
flag + docstring references + inline phase-0 comment
The original free-form rephrasings path stays (PlanConfig.
n_task_rephrasings still works when task_aug_axes.enabled=False).
Action records remain the preferred mechanism for cross-episode
subtask consistency.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
78 lines
2.7 KiB
Python
78 lines
2.7 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. 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=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 "
|
|
# 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"
|
|
)
|
|
|
|
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}")
|