You can deploy this model and start earning money today!

bhe1004/
FIRe-VLA-OpenVLA-PegInsert-Real

Name: FIRe-VLA-OpenVLA-PegInsert-Real
Availability: InStock

vision-language-action

Views

No views yet

FIRe-VLA-OpenVLA-PegInsert-Real

A OpenVLA vision-language-action policy fine-tuned for the Peg insertion contact-rich robotic assembly task (Real domain), part of the FIRe model suite.

Framework: OpenVLA
Task: Peg insertion (peg_insert)
Domain: Real
Checkpoint: inference-ready (5000 steps)

Usage

python

# Requires the OpenVLA-OFT codebase: https://github.com/moojink/openvla-oft
from transformers import AutoModelForVision2Seq, AutoProcessor

repo = "bhe1004/FIRe-VLA-OpenVLA-PegInsert-Real"
processor = AutoProcessor.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForVision2Seq.from_pretrained(repo, trust_remote_code=True)
# OFT extras bundled in the repo: action_head, proprio_projector,
# lora_adapter, dataset_statistics.json

Training data: bhe1004/FIRe-VLA-OpenVLA-PegInsert-Real

bhe1004/FIRe-VLA-OpenVLA-PegInsert-Real

FIRe-VLA-OpenVLA-PegInsert-Real

Usage

Related

bhe1004/
FIRe-VLA-OpenVLA-PegInsert-Real