Stars
A framework for prompt tuning using Intent-based Prompt Calibration
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Code and data corresponding to paper Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Python tool for converting files and office documents to Markdown.
A library to generate LaTeX expression from Python code.
If you want to become good at system design, join this newsletter now 👇
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
Forecasting Private Capital Market using published research and patents. Project developed at Michigan State University under the guidance of Dr. Mohammed Ghassemi for JP Morgan Chase.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.
Code for the paper "Feature Imitating Networks" by Sari Saba-Sadiya, Tuka Alhanai, and Mohammad M Ghassemi
Hook and simulate global keyboard events on Windows and Linux.
ICAIF 2021 Paper "A Machine Learning Approach to Detect Early Signs of Startup Success"
A JavaScript library aimed at visualizing graphs of thousands of nodes and edges
A Natural Language Processing course taught by Professor Ghassemi
Open Access PDF harvester, metadata aggregator and full-text ingester
Given a scholarly PDF, extract figures, tables, captions, and section titles.
A machine learning software for extracting information from scholarly documents
Python PDF parser for scientific publications: content and figures
Simple python parser for MEDLINE, Pubmed OA affiliation string
Graph Machine Learning, published by Packt
A python package for extracting EEG features. See article "Unsupervised EEG Artifact Detection and Correction" in Frontiers in Digital Health, 2020.
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…
Script to extract acoustic features from speech using OpenSmile toolkit.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.