QuantFactory/Thespis-Llama-3.1-8B-GGUF
Full fine-tune vs mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated. QuantFactory/Thespis-Llama-3.1-8B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 61/65, MLP 96/96, Attention 128/128, lm_head 1/1