Lightpanda: the headless browser designed for AI and automation

The headless browser for AI agents and web scraping

Headless Slay the Spire 2 CLI — play the full game from a terminal.

杀戮尖塔2自动学习

slime is an LLM post-training framework for RL Scaling.

杀戮尖塔2的MOD，将杀戮尖塔2的游戏状态与操作暴露为本地 HTTP API 包装成 MCP Server，供支持 MCP 的AI客户端直接调用

SkyRL: A Modular Full-stack RL Library for LLMs

A scalable, end-to-end training pipeline for general-purpose agents

Web Scraping Framework

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs

An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

official code repo for paper "CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

Here is a collection of checkpoints for DALLE-pytorch models, from where you can keep on training or start generating images.

A custom pytorch Dataset extension that provides a faster iteration and better RAM usage

OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from V…

Taming Transformers for High-Resolution Image Synthesis

DALL·E Mini - Generate images from a text prompt

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Train transformer language models with reinforcement learning.

A collection of libraries to optimise AI model performances

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Python PDF Parser (Not actively maintained). Check out pdfminer.six.

A tool for extracting plain text from Wikipedia dumps

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM