ulamai/Ulam-1-Small
Full fine-tune vs WeiboAI/VibeThinker-3B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 55/73, MLP 108/108, Attention 216/252
2 derivatives checked
- Flexan/ulamai-Ulam-1-Small-GGUF: Same weights, converted
- mradermacher/Ulam-1-Small-GGUF: Same weights, converted