OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Oct 9, 2024License:cc-by-nc-4.0Architecture:Transformer0.0K Open Weights Cold

OpenLLM-Ro/RoLlama3.1-8b-Instruct-DPO is an 8 billion parameter instruction-tuned generative text model built with Meta Llama 3.1, specifically optimized for the Romanian language. Developed by OpenLLM-Ro, this model excels in human-aligned instruction following and chat-based interactions in Romanian. It demonstrates strong performance across various Romanian benchmarks, including MT-Bench and RoCulturaBench, making it suitable for research and assistant-like applications in Romanian.

Loading preview...