h2stein
Follow
Stars
LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Tools for merging pretrained large language models.
🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformer…
User-friendly WebUI for LLMs (Formerly Ollama WebUI)
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…
Code for the paper "Evaluating Large Language Models Trained on Code"
OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
Data validation using Python type hints
Convert PDF to markdown quickly with high accuracy
New ways of breaking app-integrated LLMs
Large language model code completion for Emacs
🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
A TypeScript-like language for WebAssembly.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of …
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A Gradio web UI for Large Language Models.
A cheatsheet for Swift 5. Including examples of common Swift code and short explanations of what it does and how it works. Perfect for beginner iOS developers!