mradermacher/Llama-3.1-8B-FlashNorm-GGUF

Same weights, converted vs open-machine/Llama-3.1-8B-FlashNorm-test. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 1 new tensors.

Tensors changed: Norms 0/65, lm_head 0/1, Embeddings 0/1, MLP 0/96, Attention 0/128

On the Hub · Downloads on Model Pulse