Yada Pruksachatkun 's repositories
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
NLP-Resources
Code skeleton for various NLP tasks
Binder
[ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"
finetune-clm
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
Grounded-LLaVA
Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
jiant-1
jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks.
language-model-agents
Experiments with generating opensource language model assistants
mathsdl-spring20
Topics course Mathematics of Deep Learning at NYU, Spring 2020
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
personal-runners
my personal repository of training code
practicing_trustworthy_machine_learning
GitHub Repo associated with the O'Reilly book "Practicing Trustworthy Machine Learning"
pytorch-Deep-Learning
Deep Learning (with PyTorch)
sent_debias
Code for ACL 2020: Towards Debiasing Sentence Representations
st-chat
Streamlit Component, for a Chatbot UI
streamlit-stt-app
Real time web based Speech-to-Text app with Streamlit
streamlit_audio_recorder
Streamlit Custom Component that enables recording audio from the client's mic in apps that are deployed to the web. (via browser Media-API, REACT-based)
Structure-free-certified-NLP
SAFER: A Structure-free Approach For cErtified Robustness to Adversarial Word Substitutions (ACL 2020)
trl
Train transformer language models with reinforcement learning.
yanmtt
Yet Another Neural Machine Translation Toolkit