mradermacher/Llama-3.1-Minitron-4B-Depth-Base-GGUF

Same weights, converted vs nvidia/Llama-3.1-Minitron-4B-Depth-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/33, MLP 0/48, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse