apodex/Apodex-1.0-mini
Full fine-tune vs Qwen/Qwen3.5-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 280/1165, lm_head 1/1, Embeddings 1/5, Attention 243/392, other 0/1, Norms 128/247
Full fine-tune vs Qwen/Qwen3.5-35B-A3B. Fine-tune: 96% of the weights changed, across 40 of 40 layers.
Tensors changed: MLP 280/1165, lm_head 1/1, Embeddings 1/5, Attention 243/392, other 0/1, Norms 128/247