deepseek-ai / DeepSeek-VL2View external linksLinks
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
☆5,224Feb 26, 2025Updated 11 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☆4,066Apr 24, 2024Updated last year
- ☆91,854Jun 27, 2025Updated 7 months ago
- ☆101,580Aug 28, 2025Updated 5 months ago
- Janus-Series: Unified Multimodal Understanding and Generation Models☆17,706Feb 1, 2025Updated last year
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆18,273Jan 30, 2026Updated 2 weeks ago
- DeepSeek LLM: Let there be answers☆6,726Feb 4, 2024Updated 2 years ago
- DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence☆6,440Nov 11, 2025Updated 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☆9,806Sep 22, 2025Updated 4 months ago
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model☆4,996Sep 25, 2024Updated last year
- DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models☆1,894Jan 16, 2024Updated 2 years ago
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆26,595Jan 9, 2026Updated last month
- Integrate the DeepSeek API into popular softwares☆35,410Sep 25, 2025Updated 4 months ago
- Solve Visual Understanding with Reinforced VLMs☆5,841Oct 21, 2025Updated 3 months ago
- Fully open reproduction of DeepSeek-R1☆25,879Nov 24, 2025Updated 2 months ago
- DeepSeek Coder: Let the Code Write Itself☆22,776Nov 11, 2025Updated 3 months ago
- The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.☆6,526Aug 7, 2024Updated last year
- DeepEP: an efficient expert-parallel communication library☆8,984Feb 9, 2026Updated last week
- [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.☆24,446Aug 12, 2024Updated last year
- FlashMLA: Efficient Multi-head Latent Attention Kernels☆12,486Feb 6, 2026Updated last week
- ☆4,562Sep 14, 2025Updated 5 months ago
- Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities☆1,156Jul 15, 2025Updated 7 months ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆6,175Feb 3, 2026Updated last week
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models☆3,159Apr 15, 2024Updated 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…☆3,919Jun 12, 2025Updated 8 months ago
- A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone☆23,756Updated this week
- Witness the aha moment of VLM with less than $3.☆4,032May 19, 2025Updated 8 months ago
- Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving stat…☆1,544Jun 14, 2025Updated 8 months ago
- The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention☆3,330Jul 7, 2025Updated 7 months ago
- A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.☆2,918Jan 14, 2026Updated last month
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆18,503Dec 25, 2024Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆70,205Updated 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…☆3,754Nov 28, 2025Updated 2 months ago
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆13,268Updated this week
- Next-Token Prediction is All You Need☆2,345Jan 12, 2026Updated last month
- ☆553Aug 16, 2024Updated last year
- Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation☆7,965May 15, 2025Updated 9 months ago
- A fork to add multimodal model training to open-r1☆1,474Feb 8, 2025Updated last year
- Cambrian-1 is a family of multimodal LLMs with a vision-centric design.☆1,986Nov 7, 2025Updated 3 months ago
- Fast and memory-efficient exact attention☆22,231Updated this week