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 671b

82.4M Pulls 35 Tags Updated 9 months ago

deepscaler

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.

1.5b

1.2M Pulls 5 Tags Updated 1 year ago

openthinker

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

7b 32b

1.1M Pulls 15 Tags Updated 1 year ago

r1-1776

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

70b 671b

385.6K Pulls 9 Tags Updated 1 year ago

milanjeremic2/deepseek-r1-32b-uncensored

ollama run f0rc3ps/deepseek-r1-32b-uncensored:nu11secur1ty

tools

544 Pulls 1 Tag Updated 2 weeks ago

3113419790/deepseek-r1

thinking 1.5b

62 Pulls 1 Tag Updated 3 weeks ago

richardyoung/deepseek-r1-32b-uncensored

Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior

5,121 Pulls 1 Tag Updated 4 months ago

coney_/deepseek-r1_claude-sonnet4.6

thinking

519 Pulls 1 Tag Updated 1 month ago

fervent_mcclintock/deepseek-r1-0528-qwen3-8b

thinking

445 Pulls 12 Tags Updated 2 months ago

iradukundadev/finetuned-deepseek-r1_7b

Huggingface link - https://huggingface.co/iradukunda-dev/law-finetuned-DeepSeek-R1-Distill-Qwen-7B

thinking

285 Pulls 1 Tag Updated 3 months ago

imxieke/deepseek-r1

Deepseek-r1

thinking 1.5b

145 Pulls 1 Tag Updated 2 months ago

wwhyy027/deepseek-r1

thinking 7b

38 Pulls 1 Tag Updated 1 month ago

1178493925/deepseek-r1

thinking 8b

50 Pulls 1 Tag Updated 3 months ago

okamototk/deepseek-r1

DeepSeek R1 0528 Qwen3 8B with tool calling/MCP support

tools thinking 8b

2,709 Pulls 1 Tag Updated 9 months ago

lucasmg/deepseek-r1-8b-0528-qwen3-q4_K_M-tool-true

DeepSeek R1 0528 Qwen3 8B Q4 with tool calling

tools thinking

1,794 Pulls 1 Tag Updated 10 months ago

sam860/deepseek-r1-0528-qwen3

Useful DQ2 quants for deepseek-r1-0528-qwen3-distill:8b

8b

1,653 Pulls 3 Tags Updated 10 months ago

243260238/deepseek-r1-medical-demo

1.5b

25 Pulls 1 Tag Updated 2 months ago

mychen76/deepseek_r1_cline_roocode

Quantized version of DeepSeek-R1-32B optimized for tool usage with Cline / Roo Code and complex problem solving.

tools 32b

1,703 Pulls 1 Tag Updated 11 months ago

lsm03624/deepseek-r1

DeepSeek-R1-0528 仍然使用 2024 年 12 月所发布的 DeepSeek V3 Base 模型作为基座，但在后训练过程中投入了更多算力，显著提升了模型的思维深度与推理能力。这个8B精馏版本编程能力都爆表！

thinking

1,000 Pulls 1 Tag Updated 10 months ago

aratan/deepseek-r1.1

deepseek-r1.1-0528:32b update 30/05/2025 mejor que Qwen3 comparable performance to OpenAI-o3

thinking

471 Pulls 1 Tag Updated 10 months ago