How to use machinez/d3-NVFP4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="machinez/d3-NVFP4", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("machinez/d3-NVFP4", trust_remote_code=True) model = AutoModel.from_pretrained("machinez/d3-NVFP4", trust_remote_code=True, device_map="auto")
https://huggingface.co/machinez/d3-NVFP4/resolve/main/__pycache__/d3_format.cpython-310.pyc
hf download hf://machinez/d3-NVFP4/__pycache__/d3_format.cpython-310.pyc
curl -L -o d3_format.cpython-310.pyc https://huggingface.co/machinez/d3-NVFP4/resolve/main/__pycache__/d3_format.cpython-310.pyc
