Model reference · open weights

openvla-finetuned-libero-spatial

Available as managed deployment LLMs openvla Vision + text 1 variants 13k dl/mo

openvla-finetuned-libero-spatial is an open-weight language model from openvla. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byopenvla
TypeLanguage models
TaskVision + text
Parameters (lead)7.5B
Runs withtransformers
Released2024-09-03
Popularity13k downloads / month
LicenceOpen weights

About

What openvla-finetuned-libero-spatial is

This model was produced by fine-tuning the OpenVLA 7B model via LoRA (r=32) on the LIBERO-Spatial dataset from the LIBERO simulation benchmark. We made a few modifications to the training dataset to improve final performance (see the OpenVLA paper for details).

Below are the hyperparameters we used for all LIBERO experiments:

  • Hardware: 8 x A100 GPUs with 80GB memory
  • Fine-tuned with LoRA: use_lora == True, lora_rank == 32, lora_dropout == 0.0
  • Learning rate: 5e-4
  • Batch size: 128 (8 GPUs x 16 samples each)
  • Number of training gradient steps: 50K
  • No quantization at train or test time
  • No gradient accumulation (i.e. grad_accumulation_steps == 1)
  • shuffle_buffer_size == 100_000
  • Image augmentations: Random crop, color jitter (see training code for details)
Read the full model card

Usage Instructions

See the OpenVLA GitHub README for instructions on how to run and evaluate this model in the LIBERO simulator.

Citation

BibTeX:

@article{kim24openvla,
    title={OpenVLA: An Open-Source Vision-Language-Action Model},
    author={{Moo Jin} Kim and Karl Pertsch and Siddharth Karamcheti and Ted Xiao and Ashwin Balakrishna and Suraj Nair and Rafael Rafailov and Ethan Foster and Grace Lam and Pannag Sanketi and Quan Vuong and Thomas Kollar and Benjamin Burchfiel and Russ Tedrake and Dorsa Sadigh and Sergey Levine and Percy Liang and Chelsea Finn},
    journal = {arXiv preprint arXiv:2406.09246},
    year={2024}
}

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys openvla-finetuned-libero-spatial for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (openvla-finetuned-libero-spatial below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openvla-finetuned-libero-spatial","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms