janhq/Jan-v3.5-4B-gguf
Full fine-tune vs janhq/Jan-v3-4B-base-instruct. janhq/Jan-v3.5-4B-gguf is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 108/108, Norms 80/145, Attention 144/144