OpenLLM-Ro/RoMistral-7b-Instruct-2025-04-23
Full fine-tune vs mistralai/Mistral-7B-v0.3. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 18/65, MLP 96/96, Attention 128/128, lm_head 1/1
3 derivatives checked
- mradermacher/RoMistral-7b-Instruct-2025-04-23-i1-GGUF: Quantization
- mradermacher/RoMistral-7b-Instruct-2025-04-23-GGUF: Same weights, converted
- OpenLLM-Ro/RoMistral-7b-Instruct-DPO: Full fine-tune
1 other repos hold byte-for-byte identical weight files.