35 3 weeks ago

My (Gökdeniz Gülmez) first reasoning model fine-tuned on a custom distill dataset

tools thinking
882459668cff · 130B
{
"min_p": 0,
"repeat_penalty": 1,
"stop": [
"<|im_start|>",
"<|im_end|>"
],
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95
}