The A.I Megathread (LLM , GPT , Development)
"awesome-marketing-datascience/awesome-ai.md at master · underlines/awesome-marketing-datascience
Table of Contents
Large Language Models
LLaMA models
StackLLaMA: A hands-on guide to train LLaMA with RLHF
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
StackLLaMA: A hands-on guide to train LLaMA with RLHF
Published April 5, 2023Edward Beeching
Kashif Rasul
Younes Belkada
Lewis Tunstall
Leandro von Werra
Nazneen Rajani
Nathan Lambert
Models such as ChatGPT, GPT-4, and Claude are powerful language models that have been fine-tuned using a method called Reinforcement Learning from Human Feedback (RLHF) to be better aligned with how we expect them to behave and would like to use them.
In this blog post, we show all the steps involved in training a LlaMa model to answer questions on Stack Exchange with RLHF through a combination of:
Supervised Fine-tuning (SFT)
Reward / preference modeling (RM)
Reinforcement Learning from Human Feedback (RLHF)
From InstructGPT paper: Ouyang, Long, et al. "Training language models to follow instructions with human feedback." arXiv preprint arXiv:2203.02155 (2022).
By combining these approaches, we are releasing the StackLLaMA model. This model is available on the
Hub (see Meta's LLaMA release for the original LLaMA model) and the entire training pipeline is available as part of the Hugging Face TRL library. To give you a taste of what the model can do, try out the demo below!StackLLaMa is a 7 billion parameter language model based on Meta’s LLaMA model that has been trained on pairs of questions and answers from Stack Exchange using Reinforcement Learning from Human Feedback (RLHF) with the TRL library. For more details, check out our blog post.
Type in the box below and click the button to generate answers to your most pressing questions!
Intended Use: this app and its supporting model are provided as educational tools to explain RLHF with the TRL library; not to serve as replacement for human expertise. For more details on the model’s limitations in terms of factuality and biases, see the model card. Data Collection: by default, we are collecting the prompts entered in this app to further improve and evaluate the model. Do not share any personal or sensitive information while using the app! You can opt out of this data collection by removing the checkbox below:{continue reading post on site..}
https://archive.is/ujlbv
GitHub - nomic-ai/gpt4all: GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use. - nomic-ai/gpt4all
github.com
Demo, data, and code to train open-source assistant-style large language model based on GPT-J and LLaMa
Technical Report 2: GPT4All-J
Technical Report 1: GPT4All
Official Python Bindings
Official Typescript Bindings
Official Web Chat Interface
Official Chat Interface
️
Official Langchain Backend
Discord
GPT4All is made possible by our compute partner Paperspace.
Technical Report 2: GPT4All-J Technical Report 1: GPT4All Official Python Bindings Official Typescript Bindings Official Web Chat Interface Official Chat Interface️ Official Langchain BackendDiscord
GPT4All is made possible by our compute partner Paperspace.
GPT4All-J: An Apache-2 Licensed GPT4All Model
Run on an M1 Mac (not sped up!)
GPT4All-J Chat UI Installers
Installs a native chat-client with auto-update functionality that runs on your desktop with the GPT4All-J model baked into it.Mac/OSX
Windows
Ubuntu
These files are not yet cert signed by Windows/Apple so you will see security warnings on initial installation. We did not want to delay release while waiting for their process to complete.
Find the most up-to-date information on the GPT4All Website
Raw Model
ggml Model Download LinkNote this model is only compatible with the C++ bindings found here. It will not work with any existing llama.cpp bindings as we had to do a large fork of llama.cpp. GPT4All will support the ecosystem around this new C++ backend going forward.
Python bindings are imminent and will be integrated into this repository. Stay tuned on the GPT4All discord for updates.
GitHub - geekyutao/Inpaint-Anything: Inpaint anything using Segment Anything and inpainting models.
Inpaint anything using Segment Anything and inpainting models. - geekyutao/Inpaint-Anything
github.com
About
Inpaint anything using Segment Anything and inpainting models.
Inpaint Anything: Segment Anything Meets Image Inpainting
- Authors: Tao Yu, Runseng Feng, Ruoyu Feng, Jinming Liu, Xin Jin, Wenjun Zeng and Zhibo Chen.
- Institutes: University of Science and Technology of China; Eastern Institute for Advanced Study.
- Paper: arXiv (releasing)
TL; DR: Users can select any object in an image by clicking on it. With powerful vision models, e.g., SAM, LaMa and Stable Diffusion (SD), Inpaint Anything is able to remove the object smoothly (i.e., Remove Anything). Further, prompted by user input text, Inpaint Anything can fill the object with any desired content (i.e., Fill Anything) or replace the background of it arbitrarily (i.e., Replace Anything).
Inpaint Anything Features
- Remove Anything
- Fill Anything
- Replace Anything
Highlights
- Any aspect ratio supported
- 2K resolution supported
- Technical report on arXiv
- Demo Website (coming soon)
Remove Anything
|
|
|
- Click on an object;
- Segment Anything Model (SAM) segments the object out;
- Inpainting models (e.g., LaMa) fill the "hole".
Demo
|
|
|
|
|
|
|
|
|
|
|
|
Fill Anything
Text prompt: "a teddy bear on a bench"
|
|
|
Last edited:
null
...
demo site:
Sign Up - Open Assistant
OpenAssistant/oasst1 · Datasets at Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
OpenAssistant Conversations Dataset (OASST1)
Dataset Summary
In an effort to democratize research on large-scale alignment, we release OpenAssistant Conversations (OASST1), a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages distributed across 66,497 conversation trees, in 35 different languages, annotated with 461,292 quality ratings. The corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers.Please refer to our paper for further details.
OpenAssistant (OpenAssistant)
Org profile for OpenAssistant on Hugging Face, the AI community building the future.
huggingface.co
OA_Paper_2023_04_15.pdf
www.ykilcher.com
Last edited:
DeepSpeed/blogs/deepspeed-chat at master · microsoft/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective. - microsoft/DeepSpeed
github.com
DeepSpeed empowers ChatGPT-like model training with a single click, offering 15x speedup over SOTA RLHF systems with unprecedented cost reduction at all scales; learn how.
WebLLM | Home
mlc.ai
This project brings large-language model and LLM-based chatbot to web browsers. Everything runs inside the browser with no server support and accelerated with WebGPU. This opens up a lot of fun opportunities to build AI assistants for everyone and enable privacy while enjoying GPU acceleration. Please check out our GitHub repo to see how we did it. There is also a demo which you can try out.
GitHub - mlc-ai/web-llm: Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.
Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support. - GitHub - mlc-ai/web-llm: Bringing large-language models and chat to web browser...
github.com
Artificial Intelligence
Not Allen Iverson
Drake ain’t gonna like this.