API for the GPT-J language model 🦜. Including a FastAPI backend and a streamlit frontend
$ git clone https://github.com/vicgalle/gpt-j-api.gitRWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
Unofficial API Wrapper for Perplexity.ai + Account Generator with Web Interface
UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.
21 Lessons, Get Started Building with Generative AI
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Data from GitHub · snapshot Sep 24, 2026