seeyourcell

how many pictures are used to train

2

how many pictures are used to train? I use your code. Boss picture number: 300 other picture number: 300*10 ; (10 persons , everyone have 300 ). the model give...

It's said the newest dlib version also supports neon. so what is the difference with yours. which files do you modify. readme file said :reduce work load : only use...

how can train the premodel?

将llama-2-7b-chat 模型转换成 turbomind的形式，应该用哪个配置脚本去测试精度 python3 -m lmdeploy.serve.turbomind.deploy llama2 /models/llama-2-7b-chat

3

### Prerequisite - [X] I have searched [Issues](https://github.com/open-compass/opencompass/issues/) and [Discussions](https://github.com/open-compass/opencompass/discussions) but cannot get the expected help. - [X] The bug has not been fixed in the [latest version](https://github.com/open-compass/opencompass). ### Type...

the text2video result of 1.1 is worse than 1.0

3

【1.1 version】 I use the gradio/app.py prompt: # prompt_text = "A bustling city street at night, filled with the glow of car headlights and the ambient light of streetlights. The...

按照 readme 完全不能跑

how can I train the model？

deepcache support DPM \DPM etc ?

请求出错，Post "https://api.openai.com/v1/chat/completions": dial tcp 31.13.94.7:443: connectex: A connection attempt failed because the connected party did not properly respond after a period of time,

3

这个是什么原因？ 用clash 怎么设置代理啊

我看实例代码里用 train_steps = 100 inference_steps = 10 prompt = "亭台楼阁，曲径通幽，水墨绘画，中国风" olss 调度器，对 预训练的train_steps inference_steps promp 是否敏感？ 如果不同的train_steps ，inference_steps ，promp 差距很大，有无推荐；能复现论文的结果