Fast, accurate and scalable probabilistic data linkage with support for multiple SQL backends

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

OCR, Archive, Index and Search: Implementation agnostic OCR framework.

Frame Semantic Parser based on T5 and FrameNet

Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind module that scaffolds the high-level planning process by gen…

Zotero extension to retrieve and validate DOIs and shortDOIs

Open source codebase powering the HuggingChat app

Obsidian Importer lets you import notes from other apps and file formats into your Obsidian vault.

A collection of syntax highlighting snippets for Obsidian

Chatbot assistant enabling GitHub repository interaction using LLMs with Retrieval Augmented Generation

A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.

CYOA Ortho or Choose Your Own Adventure Ortho is a simple Pro Micro compatible ortho PCB that you can freely adjust to your preferences by snapping off rows or columns to make your perfect Ortho bo…

A very simple framework for state-of-the-art Natural Language Processing (NLP)

MindMaker UE4 Machine Learning Toolkit

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

Use Large Language Models like OpenAI's GPT-3.5 for data annotation and model enhancement. This framework combines human expertise with LLMs, employs Iterative Active Learning for continuous improv…

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

A simple Python sandbox for helpful LLM data agents

Official repo for NAACL 2024 Findings paper "LeTI: Learning to Generate from Textual Interactions."

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

Common Lit Augmented Student Summary Evaluation (CLASSE) corpus

A web application for interactive clustering of word senses over time.

A framework for few-shot evaluation of language models.

🦄 Unitxt: a python library for getting data fired up and set for training and evaluation

leeky - training data contamination techniques for blackbox models

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step