samunder12/llama-3.1-8b-roleplay-BSNL-gguf
Full fine-tune vs meta-llama/Llama-3.1-8B-Instruct. samunder12/llama-3.1-8b-roleplay-BSNL-gguf is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1