ProCreations/Auto-Reason-3b
Full fine-tune vs ProCreations/auto-3b. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 11/73, MLP 108/108, Attention 144/144
1 derivatives checked
- mradermacher/Auto-Reason-3b-GGUF: Same weights, converted