The Prodigy optimizer and its variants for training neural networks.

[PGAI@CIKM 2023] PyTorch Implementation of LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

The first dense retrieval model that can be prompted like an LM

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Go ahead and axolotl questions

Train GEMMA on TPU/GPU! (Codebase for training Gemma-Ko Series)

1st Place Solution for LLM - Detect AI Generated Text Kaggle Competition

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

Robust recipes to align language models with human and AI preferences

LLM Finetuning with peft

A lightning fast Finite State machine and REgular expression manipulation library.

Efficient few-shot learning with Sentence Transformers

Python logging made (stupidly) simple

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

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

⚡ TabPFN: Foundation Model for Tabular Data ⚡

https://www.kaggle.com/c/data-science-bowl-2019

Official Kaggle API

4th place solution for the Google Universal Image Embedding Kaggle Challenge. Instance-Level Recognition workshop at ECCV 2022

Image to prompt with BLIP and CLIP

1st Place Solution in Google Universal Image Embedding

2nd place solution to Google Universal Image Embedding Challenge!

An open source implementation of CLIP.

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion