Direct Preference Optimization of ChatGPT2 using TRL Library
-
Updated
Jan 24, 2024 - Jupyter Notebook
Direct Preference Optimization of ChatGPT2 using TRL Library
The overall aim of this project is to create a term rewriting system that could be useful in everyday programming, and to represent data in a way that roughly correspond to the definition of a term in formal logic. Terms should be familiar to any programmer because they are basically constants, variables, and function symbols.
ODM: TRL to BAL rules automated translation
Supervised Fine tuning using TRL library
Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch language.
Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
Add a description, image, and links to the trl topic page so that developers can more easily learn about it.
To associate your repository with the trl topic, visit your repo's landing page and select "manage topics."