Pinned Repositories
FedNLP
FedNLP: An Industry and Research Integrated Platform for Federated Learning in Natural Language Processing, Backed by FedML, Inc. The Previous Research Version is Accepted to NAACL 2022
KagNet
Knowledge-Aware Graph Networks for Commonsense Reasoning (EMNLP-IJCNLP 19)
MHGRN
Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering (EMNLP 2020)
awesome-commonsense
[Work in progress] A reading list for machine commonsense reasoning
CDMA-NER
LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
lstm_sentence_classifier
LSTM-based Models for Sentence Classification in PyTorch
OpenCSR
Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
rebiber
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
SwiftSage
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
yuchenlin's Repositories
yuchenlin/rebiber
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
yuchenlin/LLM-Blender
[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.
yuchenlin/SwiftSage
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
yuchenlin/lstm_sentence_classifier
LSTM-based Models for Sentence Classification in PyTorch
yuchenlin/OpenCSR
Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)
yuchenlin/aclpubcheck
Tools for checking ACL paper submissions
yuchenlin/petals
🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
yuchenlin/rank_outputs
yuchenlin/TextAttack
A Python framework for building adversarial attacks on NLP models
yuchenlin/acl-anthology
Data and software for building the ACL Anthology.
yuchenlin/alpaca_eval_plus
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
yuchenlin/axolotl
Go ahead and axolotl questions
yuchenlin/BIG-bench
Beyond the Imitation Game collaborative benchmark for enormous language models
yuchenlin/CEACStatTracker
CEACStatTracker
yuchenlin/CMR_fair
N/A
yuchenlin/coach
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)
yuchenlin/datasets
🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools
yuchenlin/EvalAI-NumerSense
How to create a challenge on EvalAI?
yuchenlin/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
yuchenlin/FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
yuchenlin/FedML
A Research-oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. A short version of our white paper has been accepted by NeurIPS 2020 workshop.
yuchenlin/google-research
Google Research
yuchenlin/happy-transformer
An API built on top of Hugging Face's transformer library that makes it easy to utilize state-of-the-art NLP models
yuchenlin/just-the-docs
A modern, high customizable, responsive Jekyll theme for documention with built-in search.
yuchenlin/shanzhenren.github.io
Xiang's homepage
yuchenlin/streamlit-example
Example Streamlit app that you can fork to test out share.streamlit.io
yuchenlin/transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.
yuchenlin/wiktextract
Wiktionary dump file parser and multilingual data extractor
yuchenlin/XCSR
Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"
yuchenlin/yuchenlin