mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF

Same weights, converted vs nvidia/Llama-3.1-Nemotron-70B-Instruct-HF. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1

On the Hub · Downloads on Model Pulse