Advanced Code and Text Manipulation Prompts for Various LLMs. Suitable for Deepseek, GPT o1, Claude, Llama3, Gemini, and other high-performance open-source LLMs.

s1: Simple test-time scaling

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Discord bot that uses KoboldAI. Supports tavern cards and json files.

Roleplay with AI with a focus on strong narration, consistent world and game state tracking.

Make your own story. User-friendly software for LLM roleplaying

Using Transformer deep learning architecture to predict stock prices.

TuShare is a utility for crawling historical data of China stocks

ASCII generator (image to text, image to image, video to video)

3D Visualization of an GPT-style LLM

[ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.

A framework for few-shot evaluation of language models.

PyTorch native post-training library

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

OCR, layout analysis, reading order, table recognition in 90+ languages

An automated pipeline for evaluating LLMs for role-playing.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

A family of compressed models obtained via pruning and knowledge distillation

LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

A life simulation Game powered by GPT-4's “Advanced Data Analysis” function , offering you a second chance at life. 由GPT4的Advanced Data Analysis功能驱动的人生重来模拟器，给您人生第二春。

SGLang is a fast serving framework for large language models and vision language models.

TEaR framework for paper "TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement"

Transitioning from Open-Domain Chit-Chat to Task-Oriented Dialogues