nightmedia/Qwen3.6-35B-A3B-Qwable-Holo3-Qwopus
Full fine-tune vs Hcompany/Holo3-35B-A3B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 392/392, lm_head 1/1, Embeddings 4/4, Attention 388/388, Norms 241/241
Full fine-tune vs Hcompany/Holo3-35B-A3B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 392/392, lm_head 1/1, Embeddings 4/4, Attention 388/388, Norms 241/241