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.

6 months ago

f6f38d9ed892 · 1.9GB ·

model
qwen2
·
1.78B
·
Q8_0
template
<｜begin▁of▁sentence｜>{{ if .System }}{{ .System }}{{ end }}{{ range .Messages }}{{ if eq .Ro
params
{ "num_ctx": 4096, "stop": [ "<｜end▁of▁sentence｜>" ] }

Readme

No readme