There are 14 repositories under gpt-j topic.
Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
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.
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
A GPT-J API to use with python3 to generate text, blogs, code, and more
This AI Does Not Exist: generate realistic descriptions of made-up machine learning models.
A GPT-J Chatbot Template for creating AI Characters (Virtual Girlfriend Chatbot, Stories, Roleplay, Replika-esque)
langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.
Fine-tuning 6-Billion GPT-J (& other models) with LoRA and 8-bit compression
[ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models
telegram bot for self-hosted local inference of stable diffusion, text-to-speech and large language models, such as llama3
Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance
Curated list of open source and openly accessible large language models
A Discord chatbot, based on GPT-J, trained using OKBH messages
GPT-J 6B inference on TensorRT with INT-8 precision
Vietnamese GPT-J API service deployed with Docker & Helm chart
Paraphrase generation with GPT-J on google colab!!
Natural language model AI via HTTP
Training transformer models (e.g. RoBERTa, GPT2 and GPT-J) from scratch.
Using AI to Create New Limericks Given a Topic
langchain-chat is an AI-driven Q&A system that leverages OpenAI's GPT-4 model and FAISS for efficient document indexing. It loads and splits documents from websites or PDFs, remembers conversations, and provides accurate, context-aware answers based on the indexed data. Easy to set up and extend.
AI Playground is where I build and test stuff I build with open source and custom AI and Deep Learning models
Fine-tune GPTJ for text generation task
This repository contains files for the Auto911 GPT-J based emergency response solution.
experiment, testing and build gpt-j using hugging face, deploy on sagemaker
Improving GPT-J for snippet generation.
Title and teaser generation for journalistic texts.
Production http server for our finetuned gpt-j model gptj-title-teaser-10k.