OpenLLM-Ro/RoLlama2-7b-Chat
Full fine-tune vs OpenLLM-Ro/RoLlama2-7b-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 36/65, MLP 96/96, Attention 127/128
2 derivatives checked
- legraphista/RoLlama2-7b-Chat-IMat-GGUF: Same weights, converted
- mradermacher/RoLlama2-7b-Chat-GGUF: Same weights, converted