jakeatx/slimder-qwen38-reap384-depth36-mb2-4-5
Partial fine-tune vs jakeatx/slimder-qwen38-reap384-depth40-mb4-5. Partial change: 45% of the weights changed (attention, mlp, norms), in 28 of 36 layers.
Tensors changed: lm_head 0/1, Embeddings 0/132, Norms 105/139, other 0/5, Attention 287/369, MLP 280/360
1 derivatives checked
- jakeatx/slimder-qwen38-reap384-depth36-mb2-4-5-GGUF: Not comparable yet