T145/ZEUS-8B-V24

Full fine-tune vs Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2. Fine-tune: 98% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 20/65, MLP 94/96, Attention 126/128

2 derivatives checked

• mradermacher/ZEUS-8B-V24-i1-GGUF: Quantization
• mradermacher/ZEUS-8B-V24-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse