Burnt-Toast/mn-12b-rp-but-dumb
Full fine-tune vs crestf411/nemo-sunfall-v0.6.1. 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
2 derivatives checked
- mradermacher/mn-12b-rp-but-dumb-i1-GGUF: Quantization
- mradermacher/mn-12b-rp-but-dumb-GGUF: Quantization