How to use Qwen/WorldPM-72B-UltraFeedback with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Qwen/WorldPM-72B-UltraFeedback", trust_remote_code=True)
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Qwen/WorldPM-72B-UltraFeedback", trust_remote_code=True) model = AutoModel.from_pretrained("Qwen/WorldPM-72B-UltraFeedback", trust_remote_code=True, device_map="auto")
https://huggingface.co/Qwen/WorldPM-72B-UltraFeedback/resolve/main/configuration.json
hf download hf://Qwen/WorldPM-72B-UltraFeedback/configuration.json
curl -L -o configuration.json https://huggingface.co/Qwen/WorldPM-72B-UltraFeedback/resolve/main/configuration.json
