atgctg

unsloth

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ml-engineering

Machine Learning Engineering Open Book

lm-evaluation-harness

A framework for few-shot evaluation of language models.

FriendsDontLetFriends

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

boa

Boa is an embeddable and experimental Javascript engine written in Rust. Currently, it has support for some of the language.

moondream

tiny vision language model

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

codeinterpreter-api

👾 Open source implementation of the ChatGPT Code Interpreter

cloudflare-saas-stack

Quickly make and deploy full-stack apps with database, auth, styling, storage etc. figured out for you. Add all primitives you want.

ai-toolkit

Various AI scripts. Mostly Stable Diffusion stuff.

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

L1B3RT45

JAILBREAK PROMPTS FOR LIBERATING AI MODELS

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

vimGPT

Browse the web with GPT-4V and Vimium

llm-reasoners

A library for advanced large language model reasoning

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

LLM-Blender

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

awesome-assistants

A curated list of awesome AI assistants. Example Telegram bot with all these assistants can be tested on the link below.

microagents

Agents Capable of Self-Editing Their Prompts / Python Code

cookbook

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

dom-to-semantic-markdown

DOM to Semantic-Markdown for use with LLMs

galactic

data cleaning and curation for unstructured text

bgbye

FOSS Image background remover with 10 open source rmbg models

tokenization

A comprehensive deep dive into the world of tokens

attention

visualizing attention for LLM users

globot

Globot is an agent that controls your browser using playwright and GPT-4V.

ping_pong_bench

mistral-finetuning

python-llm

A very simple cross-service LLM API for Python