# ChatML dialogue

This model is an ORPO fine-tuned version based on Mistral-7B-v0.3, integrating supervised fine-tuning and preference alignment stages, suitable for chat and text generation tasks.

Orca 2 13B is a large language model fine - tuned by Microsoft based on LLAMA - 2. It provides quantized files in GGUF format and supports efficient inference in various hardware environments.