fine-tuning-openvla-oft
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
npx skills add Orchestra-Research/AI-Research-SKILLs --skill openvla-oft --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# OpenVLA-OFT Fine-tuning and evaluation workflows for OpenVLA-OFT and OpenVLA-OFT+ from the official `openvla-oft` codebase. Covers blank-machine setup plus LoRA-based adaptation of OpenVLA for robot action generation with continuous action prediction heads. ## Quick start Clone the public repo, follow the official setup, then evaluate a pretrained LIBERO checkpoint: ```bash git clone https://github.com/moojink/openvla-oft.git cd openvla-oft python experiments/robot/libero/run_libero_eval.py \ --pretrained_checkpoint moojink/openvla-7b-oft-finetuned-libero-spatial \ --task_suite_name libero_spatial \ --center_crop True \ --num_trials_per_task 50 \ --seed 7 ``` ## Core concepts **What OpenVLA-OFT changes**: Standard OpenVLA tokenizes continuous actions into discrete bins, losing precision. OFT replaces this with dedicated continuous action heads (L1 regression or diffusion) while keeping the VLA backbone frozen and adapting via LoRA. **OFT vs OFT+ variants**: | Variant | FiLM | Images | Typical use | |---------|------|--------|-------------| | OFT | Off | 2 (front + wrist) | LIBERO simulation | | OFT+ | On | 3 (high + left + right wrist) | ALOHA real-world | **Key architecture choi
- Quick start
- Core concepts
- Compute requirements
- Expected performance benchmarks
- When to use vs alternatives
- Workflow 1: Set up environment
- Workflow 2: Evaluate pretrained checkpoints on LIBERO
- Workflow 3: Fine-tune on LIBERO
- Workflow 4: Train and evaluate OpenVLA-OFT+ on ALOHA
- Critical invariants
- Common issues
- For HPC/cluster users
- Advanced topics
- Resources
git clone https://github.com/moojink/openvla-oft.git cd openvla-oft python experiments/robot/libero/run_libero_eval.py \ conda create -n openvla-oft python=3.10 -y conda activate openvla-oft pip3 install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 pip3 install robosuite==1.4.0 pip install -e . pip install packaging ninja pip install "flash-attn==2.5.5" --no-build-isolation
What does the fine-tuning-openvla-oft skill do?
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
How do I install it?
Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill openvla-oft --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Orchestra-Research/AI-Research-SKILLs, a repository with 11,391 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.