Automating language learning with the power of Artificial Intelligence. This repository presents FluentAI, a tool that combines Fluent Forever techniques with AI-driven automation. It streamlines the process of creating Anki flashcards, making language acquisition faster and more efficient.
Problem:
Because we are now unrestricted on the imageability model, because of #52 we can use a better model for this task. We should also look into a way to upload it to huggingface so that it is useable with one of their inference APIs or their packages.
Solution:
Take a look at the mteb leaderboard: https://huggingface.co/spaces/mteb/leaderboard and try out a few of the top models for English. Also look into better methods for regression after the embeddings are generated.
Prerequisites:
None
Tasks:
Try out new embedding models
Improve code to run evaluation at once for a model that has not been generated (so it generates the embeddings automatically and uploads them to the repo)
Try out better regression models
Try uploading the model to huggingface using a transformer library (if there are any good regression models on there)
Additional context
Add any other context or screenshots about the feature request here.
Description:
Problem: Because we are now unrestricted on the imageability model, because of #52 we can use a better model for this task. We should also look into a way to upload it to huggingface so that it is useable with one of their inference APIs or their packages.
Solution: Take a look at the mteb leaderboard: https://huggingface.co/spaces/mteb/leaderboard and try out a few of the top models for English. Also look into better methods for regression after the embeddings are generated.
Prerequisites: None
Tasks:
Additional context Add any other context or screenshots about the feature request here.