bangawayoo's repositories
nlp-watermarking
Robust natural language watermarking using invariant features
adversarial-examples-in-text-classification
(ACL Findings 2022) Detection of Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
mb-lm-watermarking
multi-bit language model watermarking (NAACL 24)
bangawayoo.github.io
My github blog
clinicalnlp-mipal
Source codes for experiments on MEDIQA-M3G
FedML
A Research-oriented Federated Learning Library. Supporting distributed computing, mobile/IoT on-device training, and standalone simulation. Best Paper Award at NeurIPS 2020 Federated Learning workshop. Join our Slack Community:(https://join.slack.com/t/fedml/shared_invite/zt-havwx1ee-a1xfOUrATNfc9DFqU~r34w)
Folder-Structure-Conventions
Folder / directory structure options and naming conventions for software projects
lit-gpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
notebooks
Notebooks using the Hugging Face libraries 🤗
PSG-pytorch
Position-based Scaled Gradient for Model Quantization and Pruning Code (NeurIPS 2020)
selfcheckgpt
SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
LLaVA-Med
Large Language-and-Vision Assistant for BioMedicine, built towards multimodal GPT-4 level capabilities.
three_bricks
Official Implementation of the paper "Three Bricks to Consolidate Watermarks for LLMs"