aipib/Asagi-vlm-gguf
Full fine-tune vs llm-jp/llm-jp-3-1.8b-instruct. aipib/Asagi-vlm-gguf is a GGUF (IQ3_XXS) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 49/49, MLP 72/72, Attention 96/96