vantagewithai/Ditto-GGUF
Full fine-tune (fewer layers) vs Wan-AI/Wan2.1-T2V-14B. vantagewithai/Ditto-GGUF matches part of Wan-AI/Wan2.1-T2V-14B (216 of its 1095 tensors; the rest of Wan-AI/Wan2.1-T2V-14B has no counterpart). On the shared part: vantagewithai/Ditto-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 0 of 0 layers.
Tensors changed: Attention 128/128, Norms 48/48, MLP 32/32, other 8/8