DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance.
68.1K Pulls 1 Tag Updated 3 months ago
DeepSeek-OCR is a vision-language model that can perform token-efficient OCR.
379.5K Pulls 3 Tags Updated 4 months ago
DeepSeek-V3.1-Terminus is a hybrid model that supports both thinking mode and non-thinking mode.
542K Pulls 8 Tags Updated 6 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.
81.8M Pulls 35 Tags Updated 9 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.
3.7M 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.
2.2M Pulls 64 Tags Updated 1 year ago
A strong, economical, and efficient Mixture-of-Experts language model.
891.3K Pulls 34 Tags Updated 1 year ago
An upgraded version of DeekSeek-V2 that integrates the general and coding abilities of both DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct.
240.2K 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 version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
359.4K Pulls 9 Tags Updated 1 year ago
(Mostly) Uncensored Deepseek R1 based on unsloth/deepseek-r1-distill-qwen-7b-unsloth-bnb-4bit.
680 Pulls 1 Tag Updated 1 year ago
DeepSeek-V2.5-1210 is an upgraded version of DeepSeek-V2.5, offering enhanced mathematical, coding, writing, and reasoning capabilities.
379 Pulls 3 Tags Updated 1 year ago
Reasoning model distilled from DeepSeek-R1, enhanced with GRPO using supplementary reasoning datasets.
86 Pulls 6 Tags Updated 12 months ago
Senior Go & SpecKit engineering agent powered by DeepSeek-v3.1 671B, optimized for idiomatic development and deterministic BDD testing.
12 Pulls 1 Tag Updated 6 days ago
Based on DeepSeek R1 because OpenCode tries to verify on the registry for tool compatibility
130 Pulls 1 Tag Updated 3 weeks ago
Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior
4,861 Pulls 1 Tag Updated 4 months ago
20 Pulls 1 Tag Updated 1 week ago
NovaForge AI – DeepSeek Coder 6.7B Pro is a professional-grade coding AI built for production-level development.
1,535 Pulls 1 Tag Updated 2 months ago
783 Pulls 1 Tag Updated 2 months ago