Gryphe/Pantheon-RP-1.6-12b-Nemo
Full fine-tune vs mistralai/Mistral-Nemo-Base-2407. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 1/1
10 derivatives checked
- bartowski/Pantheon-RP-1.6-12b-Nemo-GGUF: Same weights, converted
- featherless-ai-quants/Gryphe-Pantheon-RP-1.6-12b-Nemo-GGUF: Quantization
- QuantFactory/StarDust-12b-v1-GGUF: Full fine-tune
- mradermacher/Pantheon-RP-1.6-12b-Nemo-i1-GGUF: Quantization
- QuantFactory/StarDust-12b-v2-GGUF: Full fine-tune
- mradermacher/Pantheon-RP-1.6-12b-Nemo-GGUF: Quantization
- mergekit-community/Deutscher-Pantheon-12B: Full fine-tune
- Luni/StarDust-12b-v2: Full fine-tune
- Luni/StarDust-12b-v1: Full fine-tune
- emogie3D/Mistral-Nemo-Base-2407-RP-Merge: Full fine-tune