OliviaRossi/UltiMerge
Full fine-tune (fewer layers) vs Jackrong/Qwopus3.6-35B-A3B-Coder. OliviaRossi/UltiMerge matches part of Jackrong/Qwopus3.6-35B-A3B-Coder (693 of its 1045 tensors; the rest of Jackrong/Qwopus3.6-35B-A3B-Coder has no counterpart). On the shared part: Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Attention 240/280, MLP 280/280, Norms 103/131, lm_head 1/1
1 derivatives checked
- OliviaRossi/UltiMerge-Q5_K_M-GGUF: Quantization