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.