Novaciano/Strange_Merge_Method-3.2-1B
Full fine-tune vs Novaciano/Bad_Alice-Refined-RP-3.2-1B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, lm_head 1/1, Norms 4/33, MLP 48/48, Attention 64/64
3 derivatives checked
- mradermacher/Strange_Merge_Method-3.2-1B-i1-GGUF: Quantization
- mradermacher/Strange_Merge_Method-3.2-1B-GGUF: Same weights, converted
- Novaciano/Excomunion-3.2-1B: Full fine-tune