huihui_ai/
deepseek-r1:671b-0528

153 2 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.

thinking 671b
... /
params
ed8474dc73db · 179B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
],
"temperature": 0.6,
"top_p": 0.95
}