VillanovaAI/Villanova-2B-2603

Full fine-tune vs VillanovaAI/Villanova-2B-Base-2603. Fine-tune: 100% of the weights changed, across 18 of 18 layers.

Tensors changed: Embeddings 1/1, Norms 1/37, MLP 54/54, Attention 72/72

2 derivatives checked

• mradermacher/Villanova-2B-2603-i1-GGUF: Quantization
• mradermacher/Villanova-2B-2603-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse