terryniu/
qwen1.5-7b-sft-qlora-xiaoyi:latest

16 1 year ago

We have trained a Xiaoyi dialogue robot model for the driving training field based on the Qwen1.5-7b model, using the method of QLora fine-tuning.

... /
params
9297f08dd6c6 · 65B
{
"repeat_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
}