How to use valine/GoldenGateMistral-v0-alpha with Transformers:
# Load model directly from transformers import AutoTokenizer, SplitAttentionForCasualLM tokenizer = AutoTokenizer.from_pretrained("valine/GoldenGateMistral-v0-alpha") model = SplitAttentionForCasualLM.from_pretrained("valine/GoldenGateMistral-v0-alpha")
