mradermacher/Llama-3.1-8b-Pruned-4-Layers-GGUF

Same weights, converted vs Na0s/Llama-3.1-8B-Pruned-4-Layers. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/55, MLP 0/81, Attention 0/108

On the Hub · Downloads on Model Pulse