Mungert/Trinity-Nano-Preview-GGUF
Full fine-tune vs arcee-ai/Trinity-Nano-Base. Mungert/Trinity-Nano-Preview-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 56 of 56 layers.
Tensors changed: Embeddings 1/1, Norms 224/337, MLP 222/222, Attention 280/280, lm_head 1/1