jpacifico/Chocolatine-3B-Instruct-DPO-Revised

jpacifico/Chocolatine-3B-Instruct-DPO-Revised is a 3.82 billion parameter instruction-tuned causal language model developed by Jonathan Pacifico, fine-tuned from Microsoft's Phi-3-mini-4k-instruct. This model excels in French language tasks, outperforming GPT-3.5-Turbo on MT-Bench-French, and also shows improved performance in English compared to its base model. With a 4k token context window, it is currently the best-performing 3B model on the OpenLLM Leaderboard (August 2024), demonstrating strong general capabilities.