zeroshot_topics
cappr
Our great sponsors
zeroshot_topics | cappr | |
---|---|---|
3 | 4 | |
60 | 63 | |
- | - | |
0.0 | 9.4 | |
11 months ago | about 2 months ago | |
Python | Python | |
Apache License 2.0 | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
zeroshot_topics
cappr
-
Introducing CAPPr: a package to easily perform text classification using OpenAI models
GitHub
-
[P] CAPPr: use OpenAI or HuggingFace models to easily do zero-shot text classification
While benchmarking this method on the infamous Winograd Schema Challenge, I ended up finding a 2018 paper1 w/ pretty much the same idea as CAPPr. The only difference is that CAPPr typically transposes that probability, and it naively incorporates a prior.
-
Introducing CAPPr: use OpenAI or HuggingFace models to easily do zero-shot text classification
GitHub: https://github.com/kddubey/cappr
What are some alternatives?
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
MAGIC - Language Models Can See: Plugging Visual Controls in Text Generation
TabFormer - Code & Data for "Tabular Transformers for Modeling Multivariate Time Series" (ICASSP, 2021)
zshot - Zero and Few shot named entity & relationships recognition
kogpt - KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
cleanlab - The standard package for machine learning with noisy labels and finding mislabeled data. Works with most datasets and models. [Moved to: https://github.com/cleanlab/cleanlab]
naturalspeech2-pytorch - Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
frame-semantic-transformer - Frame Semantic Parser based on T5 and FrameNet
llm-client-sdk - SDK for using LLM
awesome-open-data-annotation - Open Source Data Annotation & Labeling Tools
DDNM - [ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model