mradermacher/Lexi-Lumimaid-Llama3.1-8B-GGUF

Same weights, converted vs mrcuddle/Lexi-Lumimaid-Llama3.1-8B. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/63, MLP 0/93, Attention 0/124

On the Hub · Downloads on Model Pulse