DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
349.5K Pulls 3 Tags Updated 4 months ago
DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
54.2K Pulls 1 Tag Updated 3 months ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
479.4K Pulls 8 Tags Updated 5 months ago
DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
80.4M Pulls 35 Tags Updated 8 months ago
A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
3.7M Pulls 5 Tags Updated 1 year ago
DeepSeek Coder is a capable coding model trained on two trillion code and natural language tokens.
3.4M Pulls 102 Tags Updated 2 years ago
An open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
1.9M Pulls 64 Tags Updated 1 year ago
A strong, economical, and efficient Mixture-of-Experts language model.
687.4K Pulls 34 Tags Updated 1 year ago
An advanced language model crafted with 2 trillion bilingual tokens.
689.3K Pulls 64 Tags Updated 2 years ago
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
197.5K Pulls 7 Tags Updated 1 year ago
A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
1.2M Pulls 5 Tags Updated 1 year ago
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
912K Pulls 15 Tags Updated 11 months ago
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
304.2K Pulls 9 Tags Updated 1 year ago
5,726 Pulls 1 Tag Updated 1 year ago
16 Pulls 1 Tag Updated 3 days ago
⚠️ WARNING: All malicious actions will be punished by law.
992 Pulls 1 Tag Updated 2 weeks ago
333 Pulls 1 Tag Updated 2 weeks ago
Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility
100 Pulls 1 Tag Updated 1 week ago
Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior
4,207 Pulls 1 Tag Updated 4 months ago
31 Pulls 1 Tag Updated 2 weeks ago