JY623/KoSOLAR-v2.0

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 97/97, MLP 144/144, Attention 192/192, lm_head 1/1

2 derivatives checked

• mradermacher/KoSOLAR-v2.0-i1-GGUF: Quantization
• mradermacher/KoSOLAR-v2.0-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse