-
deepseek-r1
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
tools thinking 1.5b 7b 8b 14b 32b 70b 671b67.7M Pulls 35 Tags Updated 3 months ago
-
deepseek-v3.1
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
tools thinking cloud 671b114K Pulls 8 Tags Updated 4 weeks ago
-
deepseek-v3
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
671b2.5M Pulls 5 Tags Updated 9 months ago
-
deepseek-coder
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
1.3b 6.7b 33b1.6M Pulls 102 Tags Updated 1 year ago
-
deepseek-coder-v2
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
16b 236b1.1M Pulls 64 Tags Updated 1 year ago
-
deepseek-llm
An advanced language model crafted with 2 trillion bilingual tokens.
7b 67b211K Pulls 64 Tags Updated 1 year ago
-
deepseek-v2
A strong, economical, and efficient Mixture-of-Experts language model.
16b 236b195.8K Pulls 34 Tags Updated 1 year ago
-
deepseek-v2.5
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
236b70K Pulls 7 Tags Updated 1 year ago