JY623/KoSOLAR-v2.1
Full fine-tune vs chihoonlee10/T3Q-ko-solar-dpo-v3.0. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 16/97, MLP 144/144, Attention 192/192, lm_head 1/1
1 derivatives checked
- mradermacher/KoSOLAR-v2.1-i1-GGUF: Quantization