DeepSeek Coder is a language model project for code generation and programming tasks.
OpenVLA
OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.

About OpenVLA
OpenVLA is an open-source vision-language-action (VLA) model for robotic manipulation tasks, maintained as a public GitHub repository and built on Prismatic VLMs. It provides a codebase for training, fine-tuning, and deploying generalist robotic manipulation VLAs. The project supports arbitrary RLDS-format datasets including Open X-Embodiment data, scales model training from 1B to 34B parameters via PyTorch FSDP and Flash Attention, and offers multiple fine-tuning approaches including LoRA, partial, and full fine-tuning. It includes a lightweight inference interface compatible with HuggingFace transformers, a REST API serving script for integration with existing robot control stacks, and recent optimizations such as the OFT fine-tuning recipe and FAST action tokenizer for improved inference speed.
Key features
- Supports arbitrary RLDS-format datasets including Open X-Embodiment data
- Enables training of 1B to 34B parameter VLA models via FSDP and Flash Attention
- Built-in support for LoRA, partial, and full VLA fine-tuning
- Lightweight inference interface compatible with HuggingFace transformers
- REST API serving script for integration with robot control stacks
- Includes FAST action tokenizer for up to 15x faster discrete action inference
- Open-source repository with publicly available code, checkpoints, and model cards
- Supports scalable training of VLA models up to 34B parameters
- Provides multiple fine-tuning approaches including LoRA for efficient adaptation
OpenVLA at a glance
- Website
- github.com/openvla/openvla
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
OpenVLA alternatives
Tools and sites you could use instead, ranked by how closely they match.
DeepSWE benchmarks coding agents on original, long-horizon software engineering tasks.
MobiLlama is a small language model designed for edge devices, according to its repository description.
This repository contains the DeepSeek-V3 language model project and related source files.
ChatGLM-6B is an open bilingual dialogue language model described in English and Chinese.
xTuring supports personalizing open source language models through preprocessing and fine tuning.
Popular in Models & ML Research
Well-known listings from the same topic.
OpenVLA FAQ
What is OpenVLA?
What dataset formats are supported for training OpenVLA?
What fine-tuning options are available for OpenVLA?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












