deepseek-ai / DeepSeek-VL2Links
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
☆4,894Updated 3 months ago
Alternatives and similar repositories for DeepSeek-VL2
Users that are interested in DeepSeek-VL2 are comparing it to the libraries listed below
Sorting:
- DeepSeek-VL: Towards Real-World Vision-Language Understanding☆3,886Updated last year
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,380Updated 4 months ago
- DeepSeek LLM: Let there be answers☆6,434Updated last year
- Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆10,997Updated last month
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,909Updated 8 months ago
- DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence☆5,851Updated 8 months ago
- ☆3,363Updated 3 months ago
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models☆2,770Updated last year
- FlashMLA: Efficient MLA decoding kernels☆11,607Updated last month
- DeepSeek Coder: Let the Code Write Itself☆21,712Updated last year
- DeepEP: an efficient expert-parallel communication library☆7,911Updated this week
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆2,791Updated last week
- ☆90,136Updated 2 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆5,450Updated this week
- ☆97,630Updated this week
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,824Updated last month
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,723Updated last year
- Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…☆3,149Updated last week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆22,102Updated last week
- Fully open reproduction of DeepSeek-R1☆24,819Updated 2 weeks ago
- Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.☆5,013Updated this week
- Integrate the DeepSeek API into popular softwares☆32,851Updated last month
- Minimal reproduction of DeepSeek R1-Zero☆11,909Updated last month
- verl: Volcano Engine Reinforcement Learning for LLMs☆9,710Updated this week
- Solve Visual Understanding with Reinforced VLMs☆5,159Updated last month
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in V3/R1 training.☆2,807Updated 3 months ago
- [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型☆8,356Updated 3 weeks ago
- ☆1,527Updated 6 months ago
- SGLang is a fast serving framework for large language models and vision language models.☆15,276Updated this week
- VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…☆3,334Updated 2 weeks ago