Mungert/Trinity-Mini-GGUF
Full fine-tune vs arcee-ai/Trinity-Mini-Base. Mungert/Trinity-Mini-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 124/193, MLP 126/126, Attention 160/160, lm_head 1/1