Rupesh2/Llama-3.1-Uncensored-New

Full fine-tune vs Orenguteng/Llama-3-8B-Lexi-Uncensored. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/Llama-3.1-Uncensored-New-i1-GGUF: Quantization
• mradermacher/Llama-3.1-Uncensored-New-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse