HUJA9

0

followers

following

stars

HUJA9's starred repositories

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

Language:PythonCC-BY-SA-4.025200

TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models

Language:PythonMIT43500

awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

natural-instructions

Expanding natural instructions

Language:PythonApache-2.094900

jiant

jiant is an nlp toolkit

Language:PythonMIT163800

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

Language:PythonMIT68200

tdc2023-starter-kit

This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.

Language:PythonMIT7700

decomp_attn_keras

Parikh et al., A Decomposable Attention Model for Natural Inference

Language:Python1600

InstructEval

[NAACL 2024 Findings] Evaluation suite for the systematic evaluation of instruction selection methods.

Language:Jupyter Notebook2300

opl

Official repository for "Orthogonal Projection Loss" (ICCV'21)

Language:PythonMIT11400

TruthfulQA

TruthfulQA: Measuring How Models Imitate Human Falsehoods

Language:Jupyter NotebookApache-2.059000

Yi

A series of large language models trained from scratch by developers @01-ai

Language:Jupyter NotebookApache-2.0761800

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

Language:PythonApache-2.0685900

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Language:PythonApache-2.0184400

TransformerLens

A library for mechanistic interpretability of GPT-style language models

Language:PythonMIT144700

mteb

MTEB: Massive Text Embedding Benchmark

Language:Jupyter NotebookApache-2.0183600

prize

A prize for finding tasks that cause large language models to show inverse scaling

CC-BY-4.059300

honest_llama

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Language:PythonMIT44700

elk

Keeping language models honest by directly eliciting knowledge encoded in their activations.

Language:PythonMIT18200

promptsource

Toolkit for creating, sharing and using natural language prompts.

Language:PythonApache-2.0265400

NLPer-Conferences-Journals-Survey

Survey of NLP+AI Conferences and Journals for NLPers

MIT3800

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

Language:PythonApache-2.0650700

pytorch-grad-cam

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Language:PythonMIT1029800

adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Language:PythonMIT478500

grad-cam

[ICCV 2017] Torch code for Grad-CAM

Language:Lua148400

lost-in-the-middle

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Language:PythonMIT30300

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

Language:PythonNOASSERTION263000

ijepa

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

Language:PythonNOASSERTION279400

sleeper-agents-paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

8100

lightly

A python library for self-supervised learning on images.

Language:PythonMIT299100