Hanversion/
MAGA-T1-Tieba-1.5B-Distill:latest

47 6 months ago

This is a distill model that trained from the dataset of TieBa latest. Used about 8k data and think chain from DeepSeek-V3.

... /
params
b2ad9c47ff5f · 66B
{
"num_ctx": 4096,
"stop": [
"<｜end▁of▁sentence｜>"
]
}