matchaaaaa/MN-Tiramisu-12B

Full fine-tune vs Gryphe/Pantheon-RP-1.5-12b-Nemo. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 34/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/MN-Tiramisu-12B-i1-GGUF: Quantization
• MaziyarPanahi/MN-Tiramisu-12B-GGUF: Same weights, converted
• mradermacher/MN-Tiramisu-12B-GGUF: Quantization

On the Hub · Downloads on Model Pulse