Delta-Vector/Ohashi-NeMo-12B
Full fine-tune vs mistralai/Mistral-Nemo-Instruct-2407. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 5/81, MLP 120/120, Attention 160/160, lm_head 1/1
5 derivatives checked
- mradermacher/Ohashi-NeMo-12B-i1-GGUF: Quantization
- featherless-ai-quants/Delta-Vector-Ohashi-NeMo-12B-GGUF: Quantization
- mradermacher/Ohashi-NeMo-12B-GGUF: Quantization
- Vortex5/Moondark-12B: Full fine-tune
- Vortex5/Moonbright-12B: Full fine-tune