BGE-M3 is a multilingual text embedding model developed by the Beijing Academy of Artificial Intelligence (BAAI). It supports three retrieval methods: dense retrieval, multi-vector retrieval, and sparse retrieval for over 100 languages. This model performs excellently in the MTEB benchmark test and can effectively handle multilingual text similarity calculation and retrieval tasks.

Natural Language ProcessingTransformersMultiple Languages

A non-quantized autoregressive text-to-video model developed by Beijing Academy of Artificial Intelligence, capable of generating and editing videos based on text prompts

MultimodalDiffusers

Emu3 is a multimodal model developed by the Beijing Academy of Artificial Intelligence, trained solely by predicting the next token, supporting image, text, and video processing.

MultimodalTransformers

A Beijing dialect chat model fine-tuned based on Qwen1.5/2 large language model, recreating an authentic old Beijing chatting experience. Includes both 7B and 14B versions, specially trained with Beijing-style sitcom dialogues.

Natural Language ProcessingGgufChinese

MindLLM 1.3B is a 1.3 billion-parameter Transformer model jointly developed by the Beijing Engineering Research Center of Massive Language Information Processing and Cloud Computing Applications and the Southeast Institute of Information Technology, Beijing Institute of Technology, supporting Chinese and English dialogue generation.

Natural Language ProcessingTransformersMultiple Languages