devkit/
L1-Qwen-1.5B-Max:q8_0

68 9 months ago

Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

... /
params
f4d24e9138dd · 148B
{
"stop": [
"<｜begin▁of▁sentence｜>",
"<｜end▁of▁sentence｜>",
"<｜User｜>",
"<｜Assistant｜>"
]
}