Bansal123/maithili-mithi-2b
Full fine-tune vs unsloth/gemma-2-2b-it. Bansal123/maithili-mithi-2b is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 0/105, MLP 78/78, Attention 104/104