OpenLLM-Ro/RoGemma2-9b-Instruct-DPO-2024-10-09

Full fine-tune vs OpenLLM-Ro/RoGemma2-9b-Instruct-2024-10-09. Fine-tune: 90% of the weights changed, across 42 of 42 layers.

Tensors changed: Embeddings 0/1, Norms 116/169, MLP 126/126, Attention 168/168

1 derivatives checked

• mradermacher/RoGemma2-9b-Instruct-DPO-2024-10-09-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse