Stars
A Model Context Protocol (MCP) server that intelligently splits Markdown documents into hierarchical sections while preserving parent-child relationships and sibling connections.
100+ Fine-tuning LLM Notebooks on Google Colab, Kaggle, and more.
DSPy: The framework for programming—not prompting—language models
Agent Framework / shim to use Pydantic with LLMs
This repository contains demos I made with the Transformers library by HuggingFace.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
llama3 implementation one matrix multiplication at a time
A Python library for intelligently splitting Markdown documents into hierarchical sections while preserving their header structure and parent-child relationships.
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Convert PDF to markdown + JSON quickly with high accuracy
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.
Minimal and clean examples of machine learning algorithms implementations
The official implementation of Self-Play Fine-Tuning (SPIN)
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Best Practices on Recommendation Systems
In this project, I use a series of models to detect whether a human or a dog is present in an image. If a dog is present, the app tells the user what the dog breed is or whether it is a mutt. If it…
Implementing neural network models from scratch using NumPy, and predicting daily bike rental ridership.
Predicting the velocity of a ball thrown by an experienced handball player by measuring the accelerations captured by an inertial measuring unit attached to the player's dominant hand's wrist.
Gal-Gilor / This-Camera-is-not-for-Novices-and-Neither-is-this-Project
Forked from krbarounis/Amazon_Reviews_NLP_ProjectUsing NLP techniques and Python, we process and analyze 500K Amazon reviews to see if they align with their associated ratings, and find the most discussed topics in these reviews
In this project I've deployed different classification algorithms using Python, to predict whether a team roster is going to win a match of DOTA (Defense of The Ancients).
In this project, I'm using TensorFlow/Keras to develop a deep learning CNN to classify images of damselflies and dragonflies, reconstructing images of dragonflies.