Edentns/DataVortexS-10.7B-dpo-v1.1

Full fine-tune vs beomi/OPEN-SOLAR-KO-10.7B. Fine-tune: 98% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/192, lm_head 1/1

2 derivatives checked

• mradermacher/DataVortexS-10.7B-dpo-v1.1-i1-GGUF: Quantization
• mradermacher/DataVortexS-10.7B-dpo-v1.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse