A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.
1.5b
68.6K Pulls Updated 5 weeks ago
ed8474dc73db · 179B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
],
"temperature": 0.6,
"top_p": 0.95
}