GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized
Full fine-tune vs Qwen/Qwen2.5-VL-72B-Instruct. GeorgyGUF/INFRL-Qwen2.5-VL-72B-Preview-ggufs-fully-quantized is a GGUF (F16) of different weights. Fine-tune: 97% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 117/161, MLP 240/240, Attention 558/560, lm_head 0/1