str33t/madlad400-3b-mt-en-dv-news-v1-GGUF

Full fine-tune vs google/madlad400-3b-mt. str33t/madlad400-3b-mt-en-dv-news-v1-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 386/386, Norms 162/162, other 192/192, lm_head 1/1

On the Hub · Downloads on Model Pulse