RL4LMs
A modular RL library to fine-tune language models to human preferences
About
RL4LMs is designed for training language models to align with human preferences through customizable building blocks. It supports various NLP tasks such as summarization, dialogue generation, and machine translation, utilizing on-policy algorithms and diverse reward functions. Users can adapt the library to optimize transformer-based models on their chosen datasets, making it suitable for researchers and developers in natural language processing.
Open Source Health
- Stars
- 2,395
- Forks
- 201
- License
- Apache-2.0
- Last commit
- 3 years ago
Resources & Links
Related Categories
Vendor
Allenai
Publisher of Dont Stop Pretraining, Objaverse Xl and Procthor
Quick Links
Open Source
More by Allenai
Related Products
Dont Stop Pretraining
Code associated with the Don't Stop Pretraining ACL 2020 paper
More from this vendor
Localazy
Localazy automates translation with context-aware AI and keeps humans in control of quality.
Top category match
Lokalise
World-class AI localization platform
Top category match
The Algorithm
Source code for the X Recommendation Algorithm
Shared categories
Recommenders
TensorFlow Recommenders is a library for building recommender system models using TensorFlow.
Shared categories