YeungNLP/firefly-qwen1.5-en-7b-dpo-v0.1

YeungNLP/firefly-qwen1.5-en-7b-dpo-v0.1 is a 7.7 billion parameter Qwen1.5-based causal language model developed by YeungNLP, fine-tuned with English instruction data and further optimized using Direct Preference Optimization (DPO). This model is designed as a helpful and harmless AI assistant, demonstrating strong performance on the Open LLM Leaderboard, outperforming several larger and comparable models. It is particularly suited for English-language assistant applications and general conversational tasks.