tic-top/LoraCSE
😜Constrative Learning of Sentence Embedding using LoRA (EECS487 final project)
This project helps evaluate how well different natural language processing models can understand the similarity between sentences. You input various text sentences and get out performance scores indicating how accurately the model identifies semantic similarity. This is for machine learning researchers and NLP practitioners who are fine-tuning sentence embedding models.
No commits in the last 6 months.
Use this if you are a researcher or NLP engineer looking to compare and improve sentence embedding models, specifically using LoRA for contrastive learning.
Not ideal if you don't have access to high-end GPUs (like V100, A6000, A40) with at least 40GB of RAM, or if you're not comfortable running Python notebooks for model experimentation.
Stars
13
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Apr 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/tic-top/LoraCSE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...