🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Robust Speech Recognition via Large-Scale Weak Supervision

A natural language interface for computers

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

LlamaIndex is a data framework for your LLM applications

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Code for the paper "Language Models are Unsupervised Multitask Learners"

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective…

A Deep Learning based project for colorizing and restoring old images (and video!)

The Unified ML Representation

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Handwriting Synthesis with RNNs ✏️

Aligning pretrained language models with instruction data generated by themselves.

Seamlessly integrate LLMs into scikit-learn.

[ECCV2024] API code for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

Real-time video and audio streams over the network, with Streamlit.

A Python based RAT 🐀 (Remote Access Trojan) for getting reverse shell 🖥️

Open-Waifu open-sourced finetunable customizable simpable AI waifu inspired by neuro-sama

This repo contains a PyTorch implementation of a pretrained ERNIE model for text classification.

csvGPT is an web app tool that enables users to upload CSV files, visualize the data, and have interactive conversations with an AI model.

A WhatsApp chatbot to enable Pakistani women to learn more about their rights in Pakistan in Roman Urdu.

YoutubeGPT is a web application powered by OpenAI's Whisper model for speech recognition and GPT-3 for text summarization. It extracts transcriptions from YouTube videos and provides users with con…

Taking advantage of LlamaIndex's in-context learning paradigm, LlamaDoc empowers users to input PDF documents and pose any questions related to the content. The tool leverages the LLama Index's rea…

EmotionAI uses a CNN model to analyze facial expressions and accurately recognize emotions (happiness, sadness, anger, etc.)

ToxiScan is a text analysis tool that leverages the power of Natural Language Toolkit (NLTK) and the Naive Bayes classifier to determine the presence of toxicity in textual data.

By analyzing the linguistic complexity and repetitiveness of the text, PlagSnipe provides accurate insights into the authenticity and originality of written content, helping users identify potenti…