How to use nvidia/omnivinci with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/omnivinci", trust_remote_code=True)
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nvidia/omnivinci", trust_remote_code=True, dtype="auto")
Thank you for developring and sharing this model. My understanding is that the current model has 9B parameters. Is that correct? And are you planning to work or currently working on smaller versions of the model?
· Sign up or log in to comment
