nbeerbower/llama-3-aura-bophades-8B
Full fine-tune vs ResplendentAI/Aura_Uncensored_l3_8B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
1 derivatives checked
- mradermacher/llama-3-aura-bophades-8B-GGUF: Quantization