A comprehensive flowchart to help practitioners to find the right statistical test for their data and hypotheses.

Active Learning for Text Classification in Python

Exploring the usage of episodic knowledge graphs to create Counter-narratives (CN) for Hate Speech (HS)

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Fast and Accurate ML in 3 Lines of Code

The released data for the paper entilted "FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models"

Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the original meta-context of visual misinformation.

Playing with huggingface llama

A Simple Bulk Labelling Tool

Reliability Estimation of News Media Sources: Birds of a Feather Flock Together

Croissant is a high-level format for machine learning datasets that brings together four rich layers.

Fast bare-bones BPE for modern tokenizer training

FlexConv Pytorch Implementation with additional modules

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

1 Line of code data quality profiling & exploratory data analysis for Pandas and Spark DataFrames.

Leolani application for MMAI workshop

Python SDK for the Debate Early Access Program

Project Debater Early Access Program Tutorial

LLMFlows - Simple, Explicit and Transparent LLM Apps

🤘 The biggest collection of themes for Terminator terminal.

💽 Soothing pastel theme for Tmux

A markup-based typesetting system that is powerful and easy to learn.

Locally run an Instruction-Tuned Chat-Style LLM

Inference code for LLaMA models

Chat with Meta's LLaMA models at home made easy

High-speed download of LLaMA, Facebook's 65B parameter GPT model