stanford_alpaca
stanford_alpaca copied to clipboard
Code and documentation to train Stanford's Alpaca models, and generate the data.
I'm training a 13B model with deepspeed. Got the model to train, but the weights aren't fully saved during checkpointing. According to the HF [deepspeed docs](https://huggingface.co/transformers/v4.7.0/main_classes/deepspeed.html), the model state is...
Can I train field corpora based on the LLaMA/Alpaca Model for use in the field. what should I do? Thanks
I didn't know how to do this so I asked ChatGPT xD
Benchmarks on latest cleaned training dataset shows improvement over original published: https://github.com/gururise/AlpacaDataCleaned/issues/44#issuecomment-1494808494 
Hello, Thanks for sharing this amazing work! I tried to fine-tune Alpaca-7b. I used the same data in this repo and the same command posted in the readme file. The...
`TypeError: 'type' object is not subscriptable` is solved #171
Hey, Ruben from [Aim](https://github.com/aimhubio/aim) here! 👋 This is an awesome project! Have you considered integrating an open-source experiment tracking tool? Aim is an open-source, easy-to-use and supercharged experiment tracker. We...
Hello, I want to express my appreciation for the amazing dataset. I am curious if the dataset's creators or anyone has attempted to classify the instructions into different topics, (eg,...
Hi community, I am trying to fintune a chatbot with domain specific knowledges using alpaca way for research purpose. I do have some wikis, dialogs. does anyone know how to...
so when ever I start it it says "could not connect to [Kepar.86583]:3333" idk why it use my machine name