New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

OpenVLA-OFT Fine-Tuning

by Orchestra-Research in Orchestra-Research/AI-Research-SKILLs

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

MITAuto-check passedAI & LLM Engineering

Install OpenVLA-OFT Fine-Tuning

skills CLI
$ npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-openvla-oft -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Orchestra-Research/AI-Research-SKILLs fine-tuning-openvla-oft --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Orchestra-Research/AI-Research-SKILLs.git skills-src && mkdir -p .claude/skills && cp -r skills-src/18-multimodal/openvla-oft .claude/skills/fine-tuning-openvla-oft && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fine-tuning-openvla-oft
GitHub stars
13k
Token cost
~3.7k tokens
SKILL.md length
830 words
Files
5 (incl. references)
Skills in repo
96
Repo updated
First seen
Licence
MIT

At a glance

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups.

  • Reproducing OpenVLA-OFT results on LIBERO
  • SKILL.md covers Quick start, Core concepts, Compute requirements and Expected performance benchmarks, plus 10 more sections
  • Calls python, pip and git; reaches github.com
  • Training a custom action head, L1 or diffusion, for a robot policy

What it does

Standard OpenVLA turns continuous actions into discrete bins and loses precision. OFT replaces that with a dedicated continuous action head, either L1 regression (the default) or diffusion, keeps the backbone frozen and adapts it with a rank-32 LoRA. OFT+ switches on FiLM conditioning and uses three camera images instead of two, which suits ALOHA real-world setups, while plain OFT targets LIBERO simulation. The quick start clones the public `openvla-oft` repo and evaluates a pretrained LIBERO checkpoint.

A compute table lists a single A100 or A40 for evaluation at roughly 16 to 18 GB, and eight A100s for fine-tuning at about 27 to 35 GB per GPU. Paper results are reported with seed 7 and 50 trials per task and are tied to Python 3.10.14, PyTorch 2.2.0 and a custom Transformers fork. Reference files cover ALOHA and LIBERO workflows, config troubleshooting and paper checkpoints, and the skill helps debug normalization, LoRA merge and cross-GPU problems.

When your agent uses it

  • Reproducing OpenVLA-OFT results on LIBERO
  • Training a custom action head, L1 or diffusion, for a robot policy
  • Setting up server-client inference for an ALOHA robot
  • Debugging normalization, LoRA merge or multi-GPU problems

Example prompts

  • “Evaluate the pretrained OpenVLA-OFT LIBERO checkpoint on one task suite.”
  • “Fine-tune OFT+ with FiLM and three camera images on our ALOHA data.”
  • “Merge the LoRA weights and fix the normalization mismatch in my eval.”

Requirements

  • NVIDIA GPUs such as A100 or A40
  • Python 3.10.14 and PyTorch 2.2.0 to match paper results
  • The public `openvla-oft` repository

What it can do on your machine

Read from SKILL.md and the folder at commit 773a529. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • pip
    • git
    • conda
    • pip3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    Also links to:

    • openvla-oft.github.io
    • arxiv.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

OpenVLA-OFT Fine-Tuning loads about 3.7k tokens when it runs, and up to ~7.1k if it reads all its reference files. Until then it costs about 110 tokens; SKILL.md has 830 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~3.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Orchestra-Research/AI-Research-SKILLs at commit 773a529, republished under its MIT licence (© Orchestra-Research). 830 words, ~3,713 tokens.

Download SKILL.mdSave it as .claude/skills/fine-tuning-openvla-oft/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
fine-tuning-openvla-oft
description
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.
version
1.0.0
author
Orchestra Research
license
MIT
tags
OpenVLA, OpenVLA-OFT, VLA, Robotics, Fine-Tuning, LIBERO, ALOHA, LoRA, FiLM, Action Chunking, Deployment, Continuous Actions
dependencies
torch==2.2.0, transformers>=4.40.0, peft==0.11.1, draccus==0.8.0, accelerate>=0.25.0, wandb>=0.16.0, fastapi>=0.100.0, uvicorn>=0.24.0, tensorflow==2.15.0…

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:

VariantFiLMImagesTypical use
OFTOff2 (front + wrist)LIBERO simulation
OFT+On3 (high + left + right wrist)ALOHA real-world

Key architecture choices:

  • LoRA adaptation: Rank-32 LoRA on VLA backbone (no full fine-tuning needed)
  • Continuous actions: L1 regression head (default) or diffusion head
  • FiLM conditioning: Feature-wise Linear Modulation for stronger language grounding in OFT+
  • Multi-image input: Configurable 2 or 3 camera streams via num_images_in_input

Compute requirements

TaskGPUVRAMNotes
LIBERO evaluation1x A100/A40~16 GBSingle GPU
ALOHA evaluation1x A100/A40~18 GBSingle GPU
LIBERO fine-tuning8x A100~27 GB/GPUPaper default
ALOHA fine-tuning (OFT+)8x A100~35 GB/GPUFiLM + 3 images
LoRA merge1x any GPU~16 GBOne-time step

Expected performance benchmarks

Official results (paper setup, seed=7, 50 trials per task):

Task SuiteTask-SpecificCombined PolicyNotes
LIBERO-Spatial97.2%96.8%Easiest suite
LIBERO-Object97.4%97.0%Object manipulation
LIBERO-Goal95.8%95.4%May peak at 50k-100k steps
LIBERO-1098.0%98.0%Long-horizon tasks
Average97.1%96.8%Near-equivalent

Reproduction notes: results are tied to Python 3.10.14, PyTorch 2.2.0, NVIDIA A100, and custom Transformers fork.

When to use vs alternatives

Use OpenVLA-OFT when:

  • The target task is robot action generation with visual and language conditioning
  • LoRA-based adaptation of openvla/openvla-7b is preferred
  • You need official LIBERO or ALOHA workflows from the OpenVLA-OFT paper
  • You want continuous action heads (L1 regression or diffusion) instead of tokenized actions

Use alternatives when:

  • You need a different VLA architecture (use fine-tuning-serving-openpi for pi0/pi0.5 models)
  • You need the NVIDIA Cosmos Policy stack (use evaluating-cosmos-policy)
  • You need general LLM fine-tuning without robot action heads

Workflow 1: Set up environment

Copy this checklist and track progress:

text
Setup Progress:
- [ ] Step 1: Create conda env and install PyTorch
- [ ] Step 2: Install openvla-oft package in editable mode
- [ ] Step 3: Install FlashAttention2
- [ ] Step 4: Verify critical versions

Step 1: Create conda env and clone repo

bash
conda create -n openvla-oft python=3.10 -y
conda activate openvla-oft
git clone https://github.com/moojink/openvla-oft.git
cd openvla-oft
pip3 install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0
pip3 install robosuite==1.4.0

Step 2: Install package

bash
pip install -e .

Step 3: Install FlashAttention2

bash
pip install packaging ninja
pip install "flash-attn==2.5.5" --no-build-isolation

Step 4: Verify versions

python
import torch, transformers, peft
print(f"PyTorch: {torch.__version__}")         # Expected: 2.2.0
print(f"Transformers: {transformers.__version__}")
print(f"PEFT: {peft.__version__}")             # Expected: 0.11.1

Workflow 2: Evaluate pretrained checkpoints on LIBERO

text
LIBERO Eval Progress:
- [ ] Step 1: Install LIBERO dependencies
- [ ] Step 2: Choose checkpoint and task suite
- [ ] Step 3: Run evaluation
- [ ] Step 4: Parse and validate results

Step 1: Install LIBERO

bash
git clone https://github.com/Lifelong-Robot-Learning/LIBERO.git
pip install -e LIBERO
pip install -r experiments/robot/libero/libero_requirements.txt

Step 2: Choose checkpoint

CheckpointTask suite
moojink/openvla-7b-oft-finetuned-libero-spatiallibero_spatial
moojink/openvla-7b-oft-finetuned-libero-objectlibero_object
moojink/openvla-7b-oft-finetuned-libero-goallibero_goal
moojink/openvla-7b-oft-finetuned-libero-10libero_10
moojink/openvla-7b-oft-finetuned-libero-spatial-object-goal-10Combined

Step 3: Run evaluation

bash
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

Step 4: Parse results

python
import re

def parse_libero_log(log_path):
    """Extract per-task success rates from LIBERO eval log."""
    with open(log_path) as f:
        content = f.read()
    matches = re.findall(r"Task (.+?): (\d+)/(\d+) successes", content)
    for task, successes, trials in matches:
        rate = int(successes) / int(trials)
        print(f"  {task}: {rate:.0%} ({successes}/{trials})")

parse_libero_log("experiments/logs/latest.log")

Workflow 3: Fine-tune on LIBERO

Detailed reference: See references/libero-workflow.md for the full LIBERO setup, checkpoint selection strategy, and LoRA merge instructions.

text
LIBERO Fine-Tune Progress:
- [ ] Step 1: Prepare RLDS dataset
- [ ] Step 2: Launch torchrun with OFT defaults
- [ ] Step 3: Evaluate intermediate and final checkpoints
- [ ] Step 4: Merge LoRA for deployment if needed

Step 1: Dataset

Use RLDS datasets: libero_spatial_no_noops, libero_object_no_noops, libero_goal_no_noops, libero_10_no_noops.

Step 2: Launch training

bash
torchrun --standalone --nnodes 1 --nproc-per-node 8 vla-scripts/finetune.py \
  --vla_path openvla/openvla-7b \
  --data_root_dir /PATH/TO/RLDS/DATASETS/ \
  --dataset_name libero_spatial_no_noops \
  --run_root_dir /YOUR/CHECKPOINTS/ \
  --use_l1_regression True \
  --use_diffusion False \
  --use_film False \
  --num_images_in_input 2 \
  --use_proprio True \
  --batch_size 8 \
  --learning_rate 5e-4 \
  --num_steps_before_decay 100000 \
  --max_steps 150005 \
  --save_freq 10000 \
  --save_latest_checkpoint_only False \
  --image_aug True \
  --lora_rank 32 \
  --wandb_entity YOUR_WANDB_ENTITY \
  --wandb_project YOUR_WANDB_PROJECT

Step 3: Evaluate checkpoints

Evaluate 50k, 100k, and 150k checkpoints — LIBERO-Goal may peak earlier than other suites. Keep best checkpoint per suite by actual task success, not only training loss.

Step 4: Merge LoRA

bash
python vla-scripts/merge_lora_weights_and_save.py \
  --base_checkpoint openvla/openvla-7b \
  --lora_finetuned_checkpoint_dir /PATH/TO/CHECKPOINT_DIR
Show full SKILL.md (349 more words)Show less

Workflow 4: Train and evaluate OpenVLA-OFT+ on ALOHA

Detailed reference: See references/aloha-workflow.md for the full ALOHA server-client setup, data preprocessing, dataset registration, and troubleshooting.

text
ALOHA Progress:
- [ ] Step 1: Preprocess raw ALOHA demonstrations
- [ ] Step 2: Convert to RLDS and register dataset configs
- [ ] Step 3: Fine-tune OFT+ with FiLM and 3 images
- [ ] Step 4: Start VLA server on GPU machine
- [ ] Step 5: Run client-side robot evaluation

Step 1: Preprocess raw data

bash
python experiments/robot/aloha/preprocess_split_aloha_data.py \
  --dataset_path /path/to/aloha_raw/task_name/ \
  --out_base_dir /path/to/aloha_preprocessed/ \
  --percent_val 0.05

Step 2: Register RLDS dataset

Add entries in:

  • prismatic/vla/datasets/rlds/oxe/configs.py
  • prismatic/vla/datasets/rlds/oxe/transforms.py
  • prismatic/vla/datasets/rlds/oxe/mixtures.py

Set ALOHA constants in prismatic/vla/constants.py:

python
# Expected defaults for ALOHA
NUM_ACTIONS_CHUNK = 25        # Match control frequency (25 Hz)
ACTION_DIM = 14               # 7 joints x 2 arms
PROPRIO_DIM = 14
ACTION_PROPRIO_NORMALIZATION_TYPE = "BOUNDS"  # Absolute joint angles

Step 3: Fine-tune OFT+

bash
torchrun --standalone --nnodes 1 --nproc-per-node 8 vla-scripts/finetune.py \
  --vla_path openvla/openvla-7b \
  --data_root_dir /PATH/TO/RLDS/DATASETS/ \
  --dataset_name aloha_task_name \
  --run_root_dir /YOUR/CHECKPOINTS/ \
  --use_l1_regression True \
  --use_diffusion False \
  --use_film True \
  --num_images_in_input 3 \
  --use_proprio True \
  --batch_size 4 \
  --learning_rate 5e-4 \
  --num_steps_before_decay 50000 \
  --max_steps 100005 \
  --use_val_set True \
  --val_freq 10000 \
  --save_freq 10000 \
  --lora_rank 32

Step 4: Start VLA server (GPU machine)

bash
python vla-scripts/deploy.py \
  --pretrained_checkpoint /PATH/TO/FINETUNED/CHECKPOINT/ \
  --use_l1_regression True \
  --use_film True \
  --num_images_in_input 3 \
  --use_proprio True \
  --center_crop True \
  --unnorm_key aloha_task_name

Server listens on http://<server-ip>:8777/act.

Step 5: Run client evaluation

bash
python experiments/robot/aloha/run_aloha_eval.py \
  --center_crop True \
  --num_open_loop_steps 25 \
  --use_vla_server True \
  --vla_server_url http://<SERVER_IP>:8777 \
  --num_rollouts_planned 50 \
  --max_steps 1500

Critical invariants

These flags must be consistent between training and inference. Mismatches cause silent failures:

AreaRequired consistencyFailure if mismatched
Action headuse_l1_regression vs use_diffusionWrong head loading, invalid actions
FiLMuse_film across train/eval/deployReduced language grounding
Image streamsnum_images_in_input parityShape mismatch or performance drop
Propriouse_proprio parityState conditioning mismatch
LoRA ranklora_rank parityAdapter loading errors
Cropimage_aug=True in train → center_crop=True in evalSignificant success-rate drop
Action chunknum_open_loop_steps ≈ NUM_ACTIONS_CHUNKLatency/success tradeoff shifts
Unnorm keyunnorm_key present in checkpoint statsBad action scale

Quick validation:

python
# Verify config parity before long eval runs
train_flags = {"use_film": False, "num_images": 2, "use_proprio": True, "lora_rank": 32}
eval_flags  = {"use_film": False, "num_images": 2, "use_proprio": True, "lora_rank": 32}
for k in train_flags:
    assert train_flags[k] == eval_flags[k], f"Mismatch: {k}: {train_flags[k]} vs {eval_flags[k]}"
print("All flags consistent")

Common issues

Issue: Action quality drops after moving checkpoints across GPU types

Fix: re-merge LoRA adapter on the downstream device:

bash
python vla-scripts/merge_lora_weights_and_save.py \
  --base_checkpoint openvla/openvla-7b \
  --lora_finetuned_checkpoint_dir /PATH/TO/CHECKPOINT_DIR

Issue: Wrong action scale or failed un-normalization

Fix: check --unnorm_key matches dataset statistics in checkpoint:

python
import torch
ckpt = torch.load("checkpoint/model.pt", map_location="cpu")
print("Available norm keys:", list(ckpt.get("norm_stats", {}).keys()))

Issue: Eval success unexpectedly low

Fix: verify all invariants in the table above. Most common culprit: missing center_crop=True when trained with image_aug=True.

Issue: LIBERO eval crashes with EOFError asking for dataset path

Fix: set LIBERO_CONFIG_PATH and write a non-interactive config before headless eval.

Issue: ALOHA client ROS import fails with libffi symbol errors

Fix: conda install -c conda-forge libffi

Issue: flash-attn install fails

Fix: export TMPDIR and PIP_CACHE_DIR to the same filesystem, retry with --no-cache-dir.

Issue: EGL teardown logs show EGL_NOT_INITIALIZED

Fix: treat as teardown noise unless exit code is non-zero. Set EGL env vars:

bash
export MUJOCO_GL=egl PYOPENGL_PLATFORM=egl
export CUDA_VISIBLE_DEVICES=0 MUJOCO_EGL_DEVICE_ID=0

For HPC/cluster users

On Slurm clusters, route caches to scratch to avoid filling /home quota:

bash
export HF_HOME=/scratch/$USER/.cache/huggingface
export XDG_CACHE_HOME=/scratch/$USER/.cache
export PIP_CACHE_DIR=/scratch/$USER/.cache/pip
export TMPDIR=/scratch/$USER/tmp

Avoid stacking cluster Python modules when using conda. Typically module load cuda is sufficient.

Advanced topics

Paper summary and checkpoints: See references/paper-and-checkpoints.md Detailed LIBERO workflow: See references/libero-workflow.md Detailed ALOHA workflow: See references/aloha-workflow.md Config map and troubleshooting matrix: See references/config-troubleshooting.md

Resources

© Orchestra-Research, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in 18-multimodal/openvla-oft of Orchestra-Research/AI-Research-SKILLs.

  • SKILL.md
  • references/aloha-workflow.md
  • references/config-troubleshooting.md
  • references/libero-workflow.md
  • references/paper-and-checkpoints.md

Open the folder on GitHubat commit 773a529

Compare with similar skills

OpenVLA-OFT Fine-Tuning next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

OpenVLA-OFT Fine-Tuning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
OpenVLA-OFT Fine-Tuning this skillOrchestra-Research/AI-Research-SKILLs13k—~3.7kAutomated safety check: PassMIT
Hyperpod Version Checkerawslabs/agent-plugins916—~910Automated safety check: PassApache-2.0
Megatron-LM on SLURMNVIDIA/Megatron-LM18k—~1.8kAutomated safety check: PassApache-2.0
Coreweave Core Workflow Bjeremylongshore/tons-of-skills-marketplace2.8k—~1.2kAutomated safety check: PassMIT
GPU OptimizerMathews-Tom/armory329—~3.5kAutomated safety check: NotesMIT
Graphsignalgraphsignal/graphsignal257—~6.3kAutomated safety check: PassApache-2.0

Similar skills

  • Hyperpod Version Checker

    awslabs/agent-plugins

    Official

    Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia)…

    916 GitHub stars~910 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Megatron-LM on SLURM

    NVIDIA/Megatron-LM

    Official

    Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

    18k GitHub stars~1.8k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Coreweave Core Workflow B

    jeremylongshore/tons-of-skills-marketplace

    Run distributed GPU training jobs on CoreWeave with multi-node PyTorch.

    2.8k GitHub stars~1.2k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • GPU Optimizer

    Mathews-Tom/armory

    GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile.

    329 GitHub stars~3.5k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check: notes

  • Graphsignal

    graphsignal/graphsignal

    Profile AI inference workloads (vLLM, SGLang, TensorRT-LLM, PyTorch, any GPU application) with the Graphsignal profiler and read the results from its local /signals JSON endpoint.

    257 GitHub stars~6.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Alphagenome Finetuning

    genomicsxai/alphagenome-pytorch

    Fine-tune or transfer-learn AlphaGenome-PyTorch on custom genomic data — pick a mode (linear probe, LoRA, Locon, full), train on BigWig tracks with agt finetune, use adapters, delta checkpoints…

    162 GitHub stars~1k tokensUpdated 25 days ago
    AI & LLM EngineeringAuto-check passed

More from Orchestra-Research/AI-Research-SKILLs

All 96 skills in this repo

  • AudioCraft Audio Generation

    Orchestra-Research/AI-Research-SKILLs

    Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.

    13k GitHub starsUsed in 8 repos~3.9k tokens
    Auto-check passed

  • LLM Benchmarking with lm-evaluation-harness

    Orchestra-Research/AI-Research-SKILLs

    Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

    13k GitHub starsUsed in 8 repos~3k tokens
    Auto-check passed

  • Segment Anything Model Guide

    Orchestra-Research/AI-Research-SKILLs

    Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

    13k GitHub starsUsed in 8 repos~3.3k tokens
    Auto-check passed

  • Chroma Vector Database

    Orchestra-Research/AI-Research-SKILLs

    Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

    13k GitHub starsUsed in 7 repos~2.3k tokens
    Auto-check passed

  • CLIP Image-Text Matching

    Orchestra-Research/AI-Research-SKILLs

    Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

    13k GitHub starsUsed in 7 repos~1.7k tokens
    Auto-check passed

  • Whisper Speech Recognition

    Orchestra-Research/AI-Research-SKILLs

    Transcribes audio with OpenAI's Whisper: 99 languages, translation to English, language detection, six model sizes and word-level timestamps, from Python or the CLI.

    13k GitHub starsUsed in 7 repos~1.9k tokens
    Auto-check: notes

Works with

Categories

Questions about OpenVLA-OFT Fine-Tuning

What does OpenVLA-OFT Fine-Tuning do?

Fine-tunes and evaluates OpenVLA-OFT and OFT+ robot policies with LoRA and continuous action heads on LIBERO simulation and ALOHA real-robot setups. Standard OpenVLA turns continuous actions into discrete bins and loses precision. OFT replaces that with a dedicated continuous action head, either L1 regression (the default) or diffusion, keeps the backbone frozen and adapts it with a rank-32 LoRA.

When should I use OpenVLA-OFT Fine-Tuning?

OpenVLA-OFT Fine-Tuning fits situations like: reproducing OpenVLA-OFT results on LIBERO; training a custom action head, L1 or diffusion, for a robot policy; setting up server-client inference for an ALOHA robot; debugging normalization, LoRA merge or multi-GPU problems.

How do I install OpenVLA-OFT Fine-Tuning in Claude Code?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-openvla-oft -a claude-code`. Or copy the skill folder (18-multimodal/openvla-oft in Orchestra-Research/AI-Research-SKILLs) into .claude/skills/fine-tuning-openvla-oft in your project. Claude Code loads it when a task matches its description.

How do I install OpenVLA-OFT Fine-Tuning in Codex?

Run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-openvla-oft -a codex`. Or copy the skill folder (18-multimodal/openvla-oft in Orchestra-Research/AI-Research-SKILLs) into .agents/skills/fine-tuning-openvla-oft in your project. Codex loads it when a task matches its description.

Can I use OpenVLA-OFT Fine-Tuning in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-openvla-oft -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fine-tuning-openvla-oft, .gemini/skills/fine-tuning-openvla-oft, .github/skills/fine-tuning-openvla-oft and .opencode/skills/fine-tuning-openvla-oft in your project.

What does OpenVLA-OFT Fine-Tuning need to run?

Going by SKILL.md and its folder, OpenVLA-OFT Fine-Tuning needs the command-line tools its instructions call (python, pip, git, conda and pip3). Our summary lists: NVIDIA GPUs such as A100 or A40; Python 3.10.14 and PyTorch 2.2.0 to match paper results; The public `openvla-oft` repository.

Does OpenVLA-OFT Fine-Tuning access the network?

SKILL.md names 3 domains. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. As links in the text: openvla-oft.github.io and arxiv.org. This is read from the text; nothing was executed.

Is OpenVLA-OFT Fine-Tuning safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does OpenVLA-OFT Fine-Tuning use?

OpenVLA-OFT Fine-Tuning is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does OpenVLA-OFT Fine-Tuning use?

About 3.7k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.4k tokens, read only when the agent opens those files.

What are the alternatives to OpenVLA-OFT Fine-Tuning?

Skills that share tags, products or a category with OpenVLA-OFT Fine-Tuning: Hyperpod Version Checker (awslabs/agent-plugins, 916 stars), Megatron-LM on SLURM (NVIDIA/Megatron-LM, 18k stars), Coreweave Core Workflow B (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and GPU Optimizer (Mathews-Tom/armory, 329 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains OpenVLA-OFT Fine-Tuning?

Orchestra-Research (a GitHub organization) maintains it in Orchestra-Research/AI-Research-SKILLs, which has 13,405 GitHub stars. The repository holds 96 skills in this directory. The repository was last updated on June 16, 2026.

Source: Orchestra-Research/AI-Research-SKILLs on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.