Transformers How to use vllm-sr/d3-NVFP4-AWQ with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("zero-shot-classification", model="vllm-sr/d3-NVFP4-AWQ", trust_remote_code=True) # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModel
processor = AutoProcessor.from_pretrained("vllm-sr/d3-NVFP4-AWQ", trust_remote_code=True)
model = AutoModel.from_pretrained("vllm-sr/d3-NVFP4-AWQ", trust_remote_code=True, device_map="auto") 
