How to use chocopan/openvla_oft_plus_int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForVision2Seq model = AutoModelForVision2Seq.from_pretrained("chocopan/openvla_oft_plus_int8", trust_remote_code=True, device_map="auto")
https://huggingface.co/chocopan/openvla_oft_plus_int8/resolve/main/tokenizer.json
hf download hf://chocopan/openvla_oft_plus_int8/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/chocopan/openvla_oft_plus_int8/resolve/main/tokenizer.json
