Open Source Feature Flagging and A/B Testing Platform

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Large Concept Models: Language modeling in a sentence representation space

A generic template to create a plugin for the Cheshire Cat AI.

Plugin for the Cheshire Cat AI that hides messages for you using the farfallino alphabet.

A domain-specific language for prompt engineering

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

The HELMET Benchmark

Ontology for consent codes and data use requirements

The People’s Speech Dataset

Developer Friendly Kubernetes 👁️

RAG that intelligently adapts to your use case, data, and queries

Convert Word documents to simple and clean HTML

Convert Word documents (.docx files) to HTML

Python tool for converting files and office documents to Markdown.

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

HellaSwag: Can a Machine _Really_ Finish Your Sentence?

Appendice digitale della tesi di laurea triennale "Sviluppo e validazione di un dataset in italiano per l’analisi di stereotipi di genere nei documenti testuali" (2023) di Martino Scagnet. Universi…

Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers g…

Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

This repository contains the instruction for evaluating Text-to-SQL performances achieved by a language model on Termite Dataset

Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Python bindings for the cross-platform MIDI I/O library RtMidi

Repository for the Clic-it 2024 paper "To Click it or not to Click it"

High-quality datasets, tools, and concepts for LLM fine-tuning.