Mungert/SmolVLM-Instruct-GGUF
Full fine-tune vs HuggingFaceTB/SmolLM2-1.7B-Instruct. Mungert/SmolVLM-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Norms 49/49, MLP 72/72, Attention 96/96