akoksal / longform Goto Github PK
View Code? Open in Web Editor NEWReverse Instructions to generate instruction tuning data with corpus examples
Home Page: https://arxiv.org/abs/2304.08460
Reverse Instructions to generate instruction tuning data with corpus examples
Home Page: https://arxiv.org/abs/2304.08460
Is it possible to have a look at model fine-tuning code for the models mentioned in the paper? Thank you!
Would be specifically interested in the hyperparameters used for fine-tuning as well as how you handle the long sequences in the fine-tuning process? Are you concatenating all instructions and outputs together and split the resulting text into chunks? Are you calculating the loss for the instruction part of the input as well as for the output or only for the output (like in Alpaca)?
Hi, thanks for sharing the great work. One quick question, would you mind adding a license to the repo so that people can use it? Open license like MIT
would be great. Also I was wondering if the preprocessing scripts would be shared or not. Thanks again.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.