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