OpenLLM-Ro/RoGemma-7b-Instruct-2024-06-28
Full fine-tune vs google/gemma-7b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 49/57, MLP 84/84, Attention 112/112
1 derivatives checked
- mradermacher/RoGemma-7b-Instruct-2024-06-28-GGUF: Same weights, converted