ZhiYuan Research Institute Releases Open Source Bilingual Model Wudao・Tianying 34 Billion Aquila2-34B

The Beijing Academy of Artificial Intelligence (BAAI) has released the most powerful open-source Chinese-English large-scale model — Wudao・Skyhawk 340 billion Aquila2-34B. This new model excels in reasoning and generalization, achieving significant results in scenarios such as intelligent agents, code generation, and literature retrieval. BAAI has also launched an open-source toolkit, including the Aquila2 model series, the new version of the semantic vector model BGE, the FlagScale efficient parallel training framework, and the FlagAttention high-performance Attention operator set. These open-source projects will promote collaborative innovation in large-scale model research. The Aquila2-34B base model surpasses other open-source base models in comprehensive capabilities. The BAAI team has also developed the NLPE method to enhance the model's external capabilities. Aquila2-34B ranks second only to GPT4 in terms of reasoning ability.

ZhiYuan Research Institute Releases Emu2: A New Generation Generative Multimodal Foundation Model

["ZhiYuan Research Institute has released the new generation multimodal foundation model Emu2, pushing the boundaries of multimodal contextual learning capabilities.", "Emu2 surpasses Flamingo-80B and IDEFICS-80B, demonstrating excellent performance in few-shot multimodal understanding tasks.", "Emu2 achieves optimal performance in multiple few-shot understanding, visual question answering, and image generation tasks.", "Emu2-Chat realizes accurate understanding of text-image instructions, while Emu2-Gen offers flexible, controllable, high-quality images."]

ZhiYuan Research Institute Releases Open-Source JudgeLM Evaluation Model to Assess Various Large Models and Provide Scores

ZhiYuan Research Institute has open-sourced the JudgeLM evaluation model, which can efficiently assess various large models and provide scores. Compared to GPT-4, JudgeLM's cost is only 1/120, with a consistency rate of over 90% for evaluation results. JudgeLM can be applied in various assessment scenarios including pure text and multimodal contexts, generating scores and justifying reasons. The consistency of JudgeLM with reference answers exceeds 90%, approaching human performance. ZhiYuan Research Institute has also released datasets for training and validation samples for in-depth research on large models.

ZhiYuan Research Institute Releases 1 Billion Parameter General 3D Vision Model Uni3D

["ZhiYuan Research Institute has recently open-sourced the Uni3D model with 1 billion parameters, designed for general 3D vision tasks.", "The model can process point cloud data and has achieved breakthroughs in mainstream 3D vision tasks.", "Uni3D employs a unified Transformer architecture and introduces a multimodal alignment training method.", "The model has achieved state-of-the-art results across various 3D vision tasks.", "ZhiYuan Research Institute states that the open-source release of Uni3D will contribute to the future of 3D computing."]

ZhiYuan Releases the World's Largest Chinese-English Semantic Vector Model Training Dataset MTP

The ZhiYuan Research Institute has released the world's largest Chinese-English semantic vector model training dataset, MTP, with a data scale of 300 million pairs. MTP is the largest open-source dataset of Chinese-English related text pairs, providing an important foundation for training semantic vector models. The dataset includes Chinese-English text pairs from multiple sources, covering various types such as Q&A, comments, and news. The ZhiYuan Research Institute stated that this data plays a crucial role in training large models and will promote collaborative innovation in artificial intelligence. The release of this dataset is expected to address the shortage of training datasets for Chinese models.

ZhiYuan Research Institute Releases Open Source Bilingual Model Wudao・Tianying 34 Billion Aquila2-34B

Related Recommendations

ZhiYuan Research Institute Releases Emu2: A New Generation Generative Multimodal Foundation Model

ZhiYuan Research Institute Releases Open-Source JudgeLM Evaluation Model to Assess Various Large Models and Provide Scores

ZhiYuan Research Institute Releases 1 Billion Parameter General 3D Vision Model Uni3D

ZhiYuan Releases the World's Largest Chinese-English Semantic Vector Model Training Dataset MTP

Android Phones Copy 'Dynamic Island' Together, New Chip Power Doubles to Drive AI Features to Bloom