Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
Implements modular retrieval and inference pipelines with built-in methods like TopK retrieval and perplexity-based inference, enabling systematic benchmarking across different in-context learning strategies. Supports customizable prompt templates with placeholder-based composition and integrates with Hugging Face datasets for seamless data loading. Recently added LLaMA support and self-consistency decoding for improved reasoning tasks.
584 stars and 147 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
584
Forks
30
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 03, 2023
Monthly downloads
147
Commits (30d)
0
Dependencies
15
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Shark-NLP/OpenICL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
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".
alibaba-edu/simple-effective-text-matching-pytorch
A pytorch implementation of the ACL2019 paper "Simple and Effective Text Matching with Richer...