Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Best Practices on Recommendation Systems

Universal LLM Deployment Engine with ML Compilation

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

DSPy: The framework for programming—not prompting—foundation models

LLM Proxy to call 100+ LLM APIs using the OpenAI format - Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq

A collection of machine learning examples and tutorials.

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

A Native-PyTorch Library for LLM Fine-tuning

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

Accurate answers and instant citations for your documents.

The all-in-one LLM developer platform: prompt management, evaluation, human feedback, and deployment all in one place.

AIConfig is a config-based framework to build generative AI applications.

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.

Accelerate your Hugging Face Transformers 7.6-9x. Native to Hugging Face and PyTorch.

Question answering system for PDF files

Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.

Object detection and tracking algorithm implemented for Real-Time video streams and static images.

GPT Interviewer - Practice interview with AI interviewer based on job descriptions and resume

Web scraper with a simple REST API living in Docker and using a Headless browser and Readability.js for parsing.

Fetch, transform and plot real-time OHLC data from Coinbase using Bytewax, Bokeh and Streamlit

The idea is to calculate the similarity between the resume and the job description and then return the resumes with the highest similarity score.

Using Replicate to build Streamlit app for image generations!

fashion recommender system powered by object detection and image embedding model, with similarity search algorithm