Trappu/Magnum-Picaro-0.7-v2-12b
Full fine-tune vs Trappu/Nemo-Picaro-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 32/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/Magnum-Picaro-0.7-v2-12b-i1-GGUF: Quantization
- bartowski/Trappu_Magnum-Picaro-0.7-v2-12b-GGUF: Same weights, converted
- mradermacher/Magnum-Picaro-0.7-v2-12b-GGUF: Quantization
- featherless-ai-quants/Trappu-Magnum-Picaro-0.7-v2-12b-GGUF: Quantization