DeepSeek-R1 is a family of open reasoning models with performance approaching that of leading models, such as O3 and Gemini 2.5 Pro.
77.8M Pulls 35 Tags Updated 7 months 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.
1.1M Pulls 5 Tags Updated 12 months ago
A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.
226.3K Pulls 9 Tags Updated 11 months ago
A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.
759.3K Pulls 15 Tags Updated 10 months ago
124 Pulls 12 Tags Updated 1 week ago
Deepseek-r1
61 Pulls 1 Tag Updated 3 weeks ago
Advanced reasoning model with uncensored capabilities, perfect for complex problem-solving and unrestricted conversations without refusal behavior
2,463 Pulls 1 Tag Updated 2 months ago
10 Pulls 1 Tag Updated 3 weeks ago
Huggingface link - https://huggingface.co/iradukunda-dev/law-finetuned-DeepSeek-R1-Distill-Qwen-7B
98 Pulls 1 Tag Updated 1 month ago
基于 DeepSeek-R1-Distill-Qwen-1.5B 微调的中文轻量对话模型，自带猫娘口癖与亲昵风格。
137 Pulls 1 Tag Updated 4 months ago
38 Pulls 1 Tag Updated 1 month ago
5 Pulls 1 Tag Updated 3 weeks ago
Deepseek R1 with the Claude 3.7 Sonnet system prompt. Inspired by incept5/llama3.1-claude
5,237 Pulls 1 Tag Updated 11 months ago
DeepSeek-R1-0528-Qwen3-8B-IQ4_NL
3,201 Pulls 1 Tag Updated 8 months ago
4,225 Pulls 9 Tags Updated 11 months ago
DeepSeek R1 0528 Qwen3 8B with tool calling/MCP support
2,129 Pulls 1 Tag Updated 7 months ago
2,075 Pulls 6 Tags Updated 11 months ago
Quantized version of DeepSeek-R1-32B optimized for tool usage with Cline / Roo Code and complex problem solving.
1,576 Pulls 1 Tag Updated 9 months ago
Useful DQ2 quants for deepseek-r1-0528-qwen3-distill:8b
1,428 Pulls 3 Tags Updated 8 months ago
Deepseek R1 optimized for tool usage with Cline.
1,737 Pulls 3 Tags Updated 11 months ago