Novaciano/Pandemonium-3.2-1B
Full fine-tune vs NickyNicky/Llama-1B-GRPO_Final. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/1, Norms 33/33, MLP 48/48, Attention 64/64
2 derivatives checked
- mradermacher/Pandemonium-3.2-1B-GGUF: Same weights, converted
- Novaciano/Malbolge-3.2-1B: Full fine-tune