mradermacher/Llama-3-8B-Lexi-Uncensored-GGUF

Same weights, converted vs Orenguteng/Llama-3-8B-Lexi-Uncensored. Same weights stored in another dtype (BF16/F32 → F16/F32).

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

On the Hub · Downloads on Model Pulse