Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

GoldFinch and other hybrid transformer components

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

🔊 Text-prompted Generative Audio Model - With the ability to clone voices

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Direct Preference Optimization for RWKV, aiming for RWKV-5 and 6.

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Pre-rendered General MIDI soundfonts that can be used immediately with MIDI.js

Android JNI for port of Facebook's LLaMA model in C/C++

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …

Tools to download and cleanup Common Crawl data, updated to 2023

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Locally run an Instruction-Tuned Chat-Style LLM

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …

General fine tuning for Stable Diffusion

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

A free and unlimited API for Google Translate 💵 🚫

A package that generates the necessary token to use the Google Translate API for free 💵🚫

Diffusers Stable Diffusion as a Cog model

Stable Diffusion web UI

stable diffusion finetuned on weeb stuff

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

k_diffusion wrapper included for k_lms sampling. fixed for notebook.