LiemLin

Results 15 comments of LiemLin

> > 我也遇到了同样的问题,13B的效果比7B的要差不少。我是自己转换的模型,不知道问题出在哪里。 模型用的是下面两个: https://huggingface.co/minlik/chinese-alpaca-7b-merged https://huggingface.co/minlik/chinese-alpaca-13b-merged > > 我下载了您发布的7b模型,问答效果效果几乎没有,只会重复问题: > > ![1682922992194](https://user-images.githubusercontent.com/104432582/235417524-293ee360-8b04-4765-b806-4fcd9ade5b49.png) prompt的格式改成下面的 prompt = “Below is an instruction that describes a task. Write a response that appropriately completes the...

> > Error solved by upgrading to gcc-11. Try that first. > > That's what I did, and the error resolved. Is your operating system centos?

python server.py --listen --api

训练步骤是什么样的

基于源llama和chinese-llama-plus-lora的合并版本再训练alpaca可能会好些

![image](https://github.com/ymcui/Chinese-LLaMA-Alpaca/assets/16920347/66d88303-3fa4-44ad-8db6-39d6cd3ee615)

@sszyl 朋友你微调用了多少GPU显存,我24G显存OOM

@sszyl 兄弟你这个解决了吗 ![image](https://github.com/ymcui/Chinese-LLaMA-Alpaca/assets/16920347/1bb5b12f-f6f6-4066-a240-e7296aac4bd4) 我微调训练出来的有14G,方便的话加微信LiemLin666探讨一下啊

![image](https://github.com/ymcui/Chinese-LLaMA-Alpaca/assets/16920347/41149159-ed2a-41d5-b663-077fcc05ae71) 试试这个

![image](https://github.com/ymcui/Chinese-LLaMA-Alpaca/assets/16920347/58ffda4c-136a-4872-823f-5a612a6dfe70) 测了一下线上的ziya,也不太准确