OpenLLM-Ro/RoLlama2-7b-Instruct-2024-05-14

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 128/128

2 derivatives checked

• mradermacher/RoLlama2-7b-Instruct-2024-05-14-i1-GGUF: Quantization
• mradermacher/RoLlama2-7b-Instruct-2024-05-14-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse