huihui_ai/
deepseek-r1-abliterated:8b-0528-qwen3-q8_0

562K 3 months ago

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

thinking 1.5b 7b 8b 14b 32b 70b
... /
params
ed8474dc73db · 179B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
],
"temperature": 0.6,
"top_p": 0.95
}