zhinao/
tiny-r1:32b

123 6 months ago

Qihoo 360's first-generation reasoning model, Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.

32b

6 months ago

92a69ba150e5 · 20GB

model
qwen2
·
32.8B
·
Q4_K_M
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user
params
{ "repeat_penalty": 1.25, "stop": [ "<｜end▁of▁sentence｜>", "<|endoft

Readme

No readme