OpenLLM-Ro/RoGemma-7b-Instruct-DPO-2024-10-09

Full fine-tune vs OpenLLM-Ro/RoGemma-7b-Instruct-2024-10-09. Fine-tune: 91% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 44/57, MLP 84/84, Attention 112/112

1 derivatives checked

• mradermacher/RoGemma-7b-Instruct-DPO-2024-10-09-GGUF: Same weights, converted

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

On the Hub · Downloads on Model Pulse