Model Library
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Browse and deploy state-of-the-art AI models through the DEVUP Gateway.
Janus-Pro is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing. The decoupling not only alleviates the conflict between the visual encoder's roles in understanding and generation, but also enhances the framework's flexibility. Janus-Pro surpasses previous unified model and matches or exceeds the performance of task-specific models. The simplicity, high flexibility, and effectiveness of Janus-Pro make it a strong candidate for next-generation unified multimodal models.
DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.
The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.
DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased 10-fold to 630B tokens, while the 128K extension phase has been extended by 3.3x to 209B tokens. Additionally, DeepSeek-V3.1 is trained using the UE8M0 FP8 scale data format to ensure compatibility with microscaling data formats.
DeepSeek V3 is the model that established the architecture the rest of the line was built on. A Mixture-of-Experts design with 671B total parameters and 37B active per token, it pairs Multi-head Latent Attention with DeepSeekMoE, and introduced two ideas that have since become standard: an auxiliary-loss-free load balancing strategy, and a multi-token prediction training objective that doubles as a speculative decoding path at inference. It was the first model of this scale trained in FP8 mixed precision, on 14.8 trillion tokens, and its post-training distilled reasoning behaviour from a long chain-of-thought model without exposing a reasoning trace. It answers directly, holds a 128K context, and remains a capable general-purpose choice on DEVUP AI.
