Mungert/AFM-4.5B-GGUF
Full fine-tune vs arcee-ai/AFM-4.5B-Base. Mungert/AFM-4.5B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 58/73, MLP 72/72, Attention 144/144
Full fine-tune vs arcee-ai/AFM-4.5B-Base. Mungert/AFM-4.5B-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Norms 58/73, MLP 72/72, Attention 144/144