liutianlin0121/decoding-time-realignment
Implementation of "Decoding-time Realignment of Language Models", ICML 2024.
This tool helps AI engineers and researchers fine-tune how aligned a language model is with specific user preferences or applications, without needing to retrain the model. You provide an existing RLHF-aligned language model, and it allows you to adjust its alignment strength during the decoding (generation) process. This is for AI practitioners working on deploying or optimizing large language models.
No commits in the last 6 months.
Use this if you need to quickly adjust the alignment behavior of an already trained, RLHF-aligned language model for different use cases or to find optimal regularization strengths for future retraining, without the time and cost of full retraining.
Not ideal if you are looking to train a new language model from scratch or if your model is not already aligned using Reinforcement Learning from Human Feedback (RLHF).
Stars
21
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Jun 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/liutianlin0121/decoding-time-realignment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
luheng/deep_srl
Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next
sileod/tasksource
Datasets collection and preprocessings framework for NLP extreme multitask learning
loomchild/maligna
Bilingual sengence aligner
CK-Explorer/DuoSubs
Semantic subtitle aligner and merger for bilingual subtitle syncing.
coastalcph/lex-glue
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English