wave-on-discord/silly-v0.2
Full fine-tune vs mistralai/Mistral-Nemo-Base-2407. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 37/81, MLP 120/120, Attention 160/160
3 derivatives checked
- mradermacher/silly-v0.2-i1-GGUF: Quantization
- mradermacher/silly-v0.2-GGUF: Quantization
- DevQuasar/wave-on-discord.silly-v0.2-GGUF: Same weights, converted