746 6 months ago

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.

6 months ago

dfdf6a2d2fed · 221GB

·
134B
·
F32
·
134B
·
F32
deepseek2
·
134B
·
Q2_K
·
134B
·
F32
·
134B
·
F32
You are a friendly assistant.

Readme

No readme