Daniel TTY
Daniel TTY
I have the same issue in colab:  how should this be fixed on colab?
> What do you mean? OpenLlaMA is an open source model trained on the RedPajama dataset. You mean fine tune it using the same method Vicuna was fine tuned from...
> From our Overlord Bing: According to a Stanford announcement, Alpaca is intended only for academic research and any commercial use is prohibited. [This decision is based on three factors:...
> > > > 我发现不用自己的openai的key可以 hmm 为什么这样呢 是不是我们的api免费的结束了
@Maxwell-Lyu How about in the latest version of qlora.py? Where should I add these lines? Now they have the following lines in a new function load_data(dataset_name): else: if os.path.exists(dataset_name): try:...
mind to share the evaluation code?
are these lines of codes what is needed to make it work? cekal's amendment seems to work on the 7b version: https://huggingface.co/cekal/mpt-7b-peft-compatible/commit/a5eab52c1c61c1d50a4e01428949f6ff90c73c48 But not sure if it works fully as...
Also, datastore and other NoSQL connector for that matter
@gventuri I tried the method, but it gives error message like this before giving the correct conversational output: WARNING:pandasai.helpers.logger:Failed to execute code with a correction framework [retry number: 1] ERROR:pandasai.helpers.logger:Failed...