Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM
Full fine-tune vs zai-org/GLM-4.6V-Flash. Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM is a GGUF (IQ4_XS) of different weights. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/161, MLP 80/80, Attention 240/280, lm_head 1/1