10 actions in 10 pieces of software · ranked by words, meaning and measured trust · 638 ms

1. 1deepseek-ai/deepseek-vl2verified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-vl2

     DeepSeek-VL2, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL

2. 2deepseek-ai/deepseek-vl2-smallverified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-vl2-small

     DeepSeek-VL2-small, an advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL

3. 3chenxwh/deepseek-vl2verified and signedpassport

   modelrecord

   • chenxwh/deepseek-vl2

     Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

4. 4deepseek-vl2-tinyverified and signedpassport

   modelrecord132,881 downloads/month

   • image-text-to-text

     Task: image-text-to-text

5. 5DeepSeek-V2verified and signedpassport

   modelrecord15,621 downloads/month

   • text-generation

     Task: text-generation

6. 6deepseek-ai/deepseek-vl-7b-baseverified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-vl-7b-base

     DeepSeek-VL: An open-source Vision-Language Model designed for real-world vision and language understanding applications

7. 7deepseek-ai/deepseek-r1verified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-r1

     A reasoning model trained with reinforcement learning, on par with OpenAI o1

8. 8deepseek-ai/deepseek-v3.1verified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-v3.1

     Latest hybrid thinking model from Deepseek

9. 9deepseek-ai/deepseek-v3verified and signedpassport

   modelrecord

   • deepseek-ai/deepseek-v3

     DeepSeek-V3-0324 is the leading non-reasoning model, a milestone for open source

10. 10deepseek-ai/deepseek-67b-baseverified and signedpassport

    modelrecord

    • deepseek-ai/deepseek-67b-base

      DeepSeek LLM, an advanced language model comprising 67 billion parameters. Trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese