# Direct Preference Optimization

InternVideo2.5 is a video multimodal large language model enhanced by Long and Rich Context (LRC) modeling, built upon InternVL2.5. It significantly improves existing MLLM models by enhancing the ability to perceive fine-grained details and capture long-term temporal structures.

SimPO is a preference optimization method that eliminates the need for reference reward models, simplifying the preference alignment process.

SambaLingo-Arabic-Chat-70B is a human-aligned conversational model supporting Arabic and English, adapted and trained based on Llama-2-70b.

The SambaLingo-Turkish-Chat Model is a human preference-aligned chat model supporting Turkish and English, adapted from Llama-2-7b with Turkish language adaptation and direct preference optimization training.

A human-aligned dialogue model trained on Russian and English, optimized using Direct Preference Optimization, supporting bilingual Russian-English conversations.