shibing624 / codeassist Goto Github PK

运行training_wizardcoder_mydata.py文件时，load_dataset函数出现错误：
FileNotFoundError: Unable to find 'D:\work\workspace\gpt\webui\data/code_alpaca_20k_50.jsonl' at D:\work\workspace\gpt\webui

请问这个为什么多了一个目录前缀，导致找不到，谢谢

I am one of the authors of WizardCoder. Since our model uses the code alpaca data, WizardCoder can only be used for non-commercial usage. In your license, you write "可免费用做商业用途", which is not suitable for WizardCoder.

• I checked to make sure that this is not a duplicate issue

大佬好，清华发布了CodeGeeX2-6b，有支持的计划吗

Thanks for the great repo

i have two questions about training the models (specifically WizardCoder):

1. have you tried training with QLoRa, and not just LoRa ? are you considering adding it to the repo ?

2. the example usage (https://github.com/shibing624/CodeAssist#train-wizardcoder-model) is without ddp, only dp.
   are you sure this is the optimal setting? We got significantly higher training rates with ddp