tiiuae/Falcon-H1-3B-Instruct-GGUF
Full fine-tune vs tiiuae/Falcon-H1-3B-Base. tiiuae/Falcon-H1-3B-Instruct-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 96/96, Norms 65/65, Attention 128/128