OPPOer/Qwen-Image-Pruning
Partial fine-tune (fewer layers) vs Qwen/Qwen-Image. OPPOer/Qwen-Image-Pruning matches part of Qwen/Qwen-Image (1165 of its 1933 tensors; the rest of Qwen/Qwen-Image has no counterpart). On the shared part: Partial change: 89% of the weights changed (attention, mlp, norms, other), in 0 of 0 layers.
Tensors changed: other 128/150, Embeddings 0/4, Attention 512/576, Norms 128/147, MLP 256/288
1 derivatives checked
- ThePun1sher/Qwen-Image-Pruning-GGUF: Full fine-tune