Vennify AI
What if you want to leverage the power of GPT-3, but don’t want to wait for Open-AI to approve your application? Introducing GPT-Neo, an open-source Transformer model that resembles GPT-3 both in terms of design and performance.In this video, we’ll discuss how to implement and train GPT-Neo with just a few lines of code.
We’ll use Happy Transformer to implement GPT-Neo. Happy Transformer is an open-source Python library build on top of Hugging Face’s Transformer library to allow programmers to implement state-of-the-art NLP models with just a few lines of code.
Thank you Eleuther AI for creating and training GPT-Neo.
Article: https://www.vennify.ai/gpt-neo-made-easy/
Colab: https://colab.research.google.com/drive/1Bg3hnPOoypUi9gi1wWa2c0Voux-rPqq9?usp=sharing
Website: https://www.vennify.ai/
LinkedIn business: www.linkedin.com/company/69285475
LinkedIn personal: https://www.linkedin.com/in/ericfillion/
Happy Transformer’s GitHub: https://github.com/EricFillion/happy-transformer
Happy Transformer’s website: https://happytransformer.com/
Instagram: https://www.instagram.com/vennifyai/
Facebook: https://www.facebook.com/vennifyai
Twitter: https://twitter.com/VennifyAI
Music: www.bensound.com
Thank you for this video! I'm eager to try Happy Transformer for myself.
I'm a novice when it comes to NLP and ML, but have a keen interest in the technology. While programming in Python is no barrier, the documentation for NLP tools are often heavily slanted for people who already have a background in ML or data science in general. Might you consider a video that explains some of the rarified nomenclature that is often used when describing how to make use of frameworks like Happy Transformers? For example, what is an n-gram, logit, or an embed in practical terms? What is the best way to format text data for finetuning? I often feel like I'm drowning in a world of exotic terminology.
I'd love to see more videos about GPT-Neo! Great job
Thanks a lot. awesome … is better to use the GPT-Neo simple model than the large one if I want to fine-tune on my dataset?
How it is different from Etherium AI
so if 2.7B takes 12GB of vram
then 270B might take 1200GB of VRAM?
Anyone got $2M to rent a bigass Amazon server? 😀 Maybe someone can start a kickstarter?