liminerity/llama-lexi-star-uncensored-8b-slerp

Full fine-tune vs Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 9/65, MLP 93/96, Attention 124/128, lm_head 0/1

1 derivatives checked

• mradermacher/llama-lexi-star-uncensored-8b-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse