Simon Yu's repositories
deep-casas
Deep learning and LSTM approaches for human activity recognition
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
adv-retreival-icl
Codebase for the paper "Evaluating the Adversarial Robustness of Retrieval-Based In-Context Learning for Large Language Models"
AL-Smarthome
AL Activity Learning for the Smarthome
arena-hard-auto
Arena-Hard-Auto: An automatic LLM benchmark.
DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
deita
Deita: Data-Efficient Instruction Tuning for Alignment
DKN
A tensorflow implementation of DKN (Deep Knowledge-aware Network for News Recommendation)
HiAGM
Hierarchy-Aware Global Model for Hierarchical Text Classification
helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
HiMatch
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification
HTCInfoMax
The code for our NAACL 2021 paper "HTCInfoMax: A Global Model for Hierarchical Text Classification via Information Maximization".
Library-books-system
Book Library management
lost-in-the-middle
Code and data for "Lost in the Middle: How Language Models Use Long Contexts"
mvp
Official Repository for the paper "Model-tuning Via Prompts Makes NLP Models More Robust"
RULER
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
Search-the-closest-Branch-by-AI
Talk with our AI no!
SelfAware
Large Language Models are more Self-Aware
Seq_IT
The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from alpaca-lora and LAVIS
TextAttack
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
trl
Train transformer language models with reinforcement learning.