mradermacher/SELM-Llama-3-8B-Instruct-iter-1-GGUF
Partial fine-tune vs jcmei/SELM-Llama-3-8B-Instruct-iter-1. mradermacher/SELM-Llama-3-8B-Instruct-iter-1-GGUF is a GGUF (F16) of different weights. Partial change: 56% of the weights changed (attention, lm_head, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 9/65, MLP 52/96, Attention 83/128, lm_head 1/1