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.

axolotl

Go ahead and axolotl questions

rebiber

A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

alpaca_eval_plus

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

yuchenlin

SwiftSage

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

OpenCSR

Code Repo for "Differentiable Open-Ended Commonsense Reasoning" (NAACL 2021)

shanzhenren.github.io

Xiang's homepage

rank_outputs

aclpubcheck

Tools for checking ACL paper submissions

petals

🌸 Run 100B+ language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

streamlit-example

Example Streamlit app that you can fork to test out share.streamlit.io

CMR_fair

N/A

CEACStatTracker

CEACStatTracker

acl-anthology

Data and software for building the ACL Anthology.

transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

XCSR

Code Repo for the ACL21 paper "Common Sense Beyond English: Evaluating and Improving Multilingual LMs for Commonsense Reasoning"

BIG-bench

Beyond the Imitation Game collaborative benchmark for enormous language models

just-the-docs

A modern, high customizable, responsive Jekyll theme for documention with built-in search.

EvalAI-NumerSense

How to create a challenge on EvalAI?

datasets

🤗 The largest hub of ready-to-use NLP datasets for ML models with fast, easy-to-use and efficient data manipulation tools

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.

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

wiktextract

Wiktionary dump file parser and multilingual data extractor

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

google-research

Google Research

lstm_sentence_classifier

LSTM-based Models for Sentence Classification in PyTorch

TextAttack

A Python framework for building adversarial attacks on NLP models

coach

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)