DeepSeek Reasoner

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

89.9M Pulls 35 Tags Updated 1 year ago

huihui_ai/deepseek-r1-abliterated

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

thinking 1.5b 7b 8b 14b 32b 70b

709.5K Pulls 55 Tags Updated 1 year ago

MFDoom/deepseek-r1-tool-calling

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen. With Tool Calling support.

tools 1.5b 7b 8b 14b 32b 70b 671b

77.3K Pulls 26 Tags Updated 1 year ago

Mrs_peanutbutt3r/deepseek-r1-coder-tools

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1. Compatible with Cline. Distill Versions are available! <3

1.5b 7b 8b 14b 32b 70b

1,366 Pulls 20 Tags Updated 1 year ago

org/deepseek-r1-uncensored

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

1,145 Pulls 4 Tags Updated 1 year ago

huihui_ai/deepseek-r1

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

thinking 671b

308 Pulls 12 Tags Updated 1 year ago

emsi/r1-1776

R1 1776 is a DeepSeek-R1 reasoning model that has been post-trained by Perplexity AI to remove Chinese Communist Party censorship.

261 Pulls 2 Tags Updated 1 year ago

milkey/deepseek-r1-UD

(Unsloth Dynamic Quants) DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, 671B MoE full model, not dense distilled models.

204 Pulls 2 Tags Updated 1 year ago