grimjim/MagnaRei-v2-12B
Full fine-tune vs Delta-Vector/Rei-V2-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 31/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/MagnaRei-v2-12B-i1-GGUF: Quantization
- mradermacher/MagnaRei-v2-12B-GGUF: Quantization
- grimjim/MagnaMellRei-v1-12B: Full fine-tune
- grimjim/MagSoup-v1-12B: Full fine-tune