Framework for building conversational agents using a Finite State Machine (FSM) and LLMs

Mamba SSM architecture

This list is meant to be both a quick guide and deep dive into what your primary focus should be when it comes to learning Data Structures and Algorithms.

Source content for the Qiskit Textbook

Implementation of Nougat Neural Optical Understanding for Academic Documents

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

A simple and effective LLM pruning approach.

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

Collection of Summer 2025 tech internships!

A nanoGPT pipeline packed in a spreadsheet

Grok open release

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

This repo consists of examples to use langchain

Examples in the MLX framework

A multi-platform SwiftUI frontend for running local LLMs with Apple's MLX framework.

A simple script to enhance text editing across your Mac, leveraging the power of MLX. Designed for seamless integration, it offers real-time text correction everywhere you type.

Get started with CORD-19

Yahoo Knowledge COVID-19 API provides JSON-API and GraphQL interfaces to access COVID-19 publicly sourced data

An all-in-one LLMs Chat UI for Apple Silicon Mac using MLX Framework.

Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

A reinforcement learning framework based on MLX.

MLX: An array framework for Apple silicon

Create Custom GPT and add/embed on your site using Assistants api

A "personal" website made for Eleanor Swift, our GHW November character for showing portfolio building concepts.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.