🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.

🤖 𝗟𝗲𝗮𝗿𝗻 for 𝗳𝗿𝗲𝗲 how to 𝗯𝘂𝗶𝗹𝗱 an end-to-end 𝗽𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝗼𝗻-𝗿𝗲𝗮𝗱𝘆 𝗟𝗟𝗠 & 𝗥𝗔𝗚 𝘀𝘆𝘀𝘁𝗲𝗺 using 𝗟𝗟𝗠𝗢𝗽𝘀 best practices: ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 12 𝘩𝘢𝘯𝘥𝘴-𝘰𝘯 𝘭𝘦𝘴𝘴𝘰𝘯𝘴

Rank LLMs, RAG systems, and prompts using automated judge evaluation

🙌 OpenHands: Code Less, Make More

Code for evaluating with Flow-Judge-v0.1 - an open-source, lightweight (3.8B) language model optimized for LLM system evaluations. Crafted for accuracy, speed, and customization.

Lightweight tools for quick and easy LLM demo's

This repository contains demos I made with the Transformers library by HuggingFace.

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

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Python Deep Dive Course - Accompanying Materials

The simplest, fastest repository for training/finetuning medium-sized GPTs.

LLM101n: Let's build a Storyteller

The Mojo Programming Language

LLM training in simple, raw C/CUDA

port of Andrjey Karpathy's llm.c to Mojo

Fully open-source client that streamlines your merging operations with the convenience of a GUI interface. Underneath, flow-merge-ui is based on the flow-merge library.

llama3 implementation one matrix multiplication at a time

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Evaluate your LLM's response with Prometheus and GPT4 💯

All-in-one AI CLI tool featuring Chat-REPL, Shell Assistant, RAG, AI tools & agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

High-quality datasets, tools, and concepts for LLM fine-tuning.

This project is aimed at automating test cases for an ecommerce store Balticlovers.pl, using Selenium and Python.

A framework for few-shot evaluation of language models.

flow-merge is a powerful Python library that enables seamless merging of multiple transformer-based language models using the most popular merge methods such as model soups, SLERP, ties-MERGING or …

The official Meta Llama 3 GitHub site

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

Official repository of Evolutionary Optimization of Model Merging Recipes

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.