nbeerbower/Stella-mistral-nemo-12B-v2
Full fine-tune vs nbeerbower/Lyra-Gutenberg-mistral-nemo-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 47/81, MLP 120/120, Attention 160/160, lm_head 1/1
4 derivatives checked
- mradermacher/Stella-mistral-nemo-12B-v2-i1-GGUF: Quantization
- QuantFactory/Book-Gut12B-GGUF: Full fine-tune
- mradermacher/Stella-mistral-nemo-12B-v2-GGUF: Quantization
- ClaudioItaly/Book-Gut12B: Full fine-tune