Nelson Liu's repositories
lost-in-the-middle
Code and data for "Lost in the Middle: How Language Models Use Long Contexts"
evaluating-verifiability-in-generative-search-engines
Companion repo for "Evaluating Verifiability in Generative Search Engines".
word2color
Given a description of a color, return its closest standard HTML4 color.
Adv360-Pro-ZMK
Production repository for the all-new Advantage360 Professional using ZMK engine
alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
codalab-worksheets
A collaborative platform for reproducible research (web interface and CLI).
DefinitelyTyped
The repository for high quality TypeScript type definitions.
dom-distiller
Distills the DOM
editdistance-feedstock
A conda-smithy repository for editdistance.
galai
Model API for GALACTICA
helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
HolisticTraceAnalysis
A library to analyze PyTorch traces.
llama-recipes
Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger
opentelemetry-python
OpenTelemetry Python API and SDK
pandas
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
react-autosuggest
WAI-ARIA compliant React autosuggest component
react-hash-link
Painless hash link routing for React applications.
ReadabiliPy
A simple HTML content extractor in Python. Can be run as a wrapper for Mozilla's Readability.js package or in pure-python mode.
simple-wikidata-db
A set of Python scripts for preprocessing the Wikidata JSON dump and running simple queries in an efficient manner.
SummEval
Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
toma
Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.
url-change-event
a wrapper event that listen & control URL changes
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs