How to use baseten/v3-nextn-head0 with Transformers:
# Load model directly from transformers import AutoTokenizer, DeepseekV3ForCausalLMNextN tokenizer = AutoTokenizer.from_pretrained("baseten/v3-nextn-head0", trust_remote_code=True) model = DeepseekV3ForCausalLMNextN.from_pretrained("baseten/v3-nextn-head0", trust_remote_code=True)
