MFDoom/
deepseek-r1-tool-calling:1.5b-qwen-distill-q8_0

24.5K 8 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. With Tool Calling support.

tools 1.5b 7b 8b 14b 32b 70b 671b
... /
params
33fd32dbc732 · 164B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
],
"temperature": 0
}