yamatazen/NeonMaid-12B

Full fine-tune vs Delta-Vector/Francois-PE-V2-Huali-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 76/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/NeonMaid-12B-i1-GGUF: Quantization
• mradermacher/NeonMaid-12B-GGUF: Quantization
• yamatazen/NeonMaid-12B-v2: Partial fine-tune

On the Hub · Downloads on Model Pulse