proserve

ui

Beautifully designed components that you can copy and paste into your apps. Accessible. Customizable. Open Source.

ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

appwrite

Your backend, minus the hassle.

Fooocus

Focus on prompting and generating

jsoncrack.com

✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.

GPTs

leaked prompts of GPTs

ChatDev

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

nginx-proxy-manager

Docker container for managing Nginx proxy hosts with a simple, powerful interface

mlc-llm

Universal LLM Deployment Engine with ML Compilation

marker

Convert PDF to markdown quickly with high accuracy

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

tinacms

A fully open-source headless CMS that supports Markdown and Visual Editing

amazon-sagemaker-examples

Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

udlbook

Understanding Deep Learning - Simon J.D. Prince

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

OpenCopilot

🤖 🔥 Language-to-actions engine

gpt-llm-trainer

Doctor-Dignity

Doctor Dignity is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.

deepeval

The LLM Evaluation Framework

LLM-Finetuning

LLM Finetuning with peft

P-tuning-v2

An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

distilabel

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

SoM

Set-of-Mark Prompting for LMMs

texify

Math OCR model that outputs LaTeX and markdown

NEFTune

Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning

libgen_to_txt

Convert all of libgen to high quality markdown

llama-inference

experiments with inference on llama

chapterize

A simple tool for splitting up an ebook into its chapters. Works well with Project Gutenberg texts. May also be used to clean up books for computational text analysis.