OpenLLM-Ro/RoMistral-7b-Instruct-2024-05-17
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 16/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/RoMistral-7b-Instruct-2024-05-17-i1-GGUF: Quantization
- mradermacher/RoMistral-7b-Instruct-2024-05-17-GGUF: Same weights, converted
- tensorblock/RoMistral-7b-Instruct-2024-05-17-GGUF: Quantization