How to use WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a", dtype="auto")
takes a long time to infer on two 3090, while does not response, I wonder why?
· Sign up or log in to comment
