mradermacher/Llama-3-8B-Instruct-262k-GGUF
Full fine-tune vs gradientai/Llama-3-8B-Instruct-262k. mradermacher/Llama-3-8B-Instruct-262k-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 33/65, MLP 96/96, Attention 128/128, lm_head 1/1