How to use sgowdaks/falcon-40b-instruct-8bit with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sgowdaks/falcon-40b-instruct-8bit", trust_remote_code=True, dtype="auto")
No model card
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sgowdaks/falcon-40b-instruct-8bit", trust_remote_code=True, dtype="auto")