HuggingFace Crash Course - Sentiment Analysis, Model Hub, Fine Tuning

Patrick Loeber
Patrick Loeber
113.8 هزار بار بازدید - 3 سال پیش - In this video I show
In this video I show you everything to get started with Huggingface and the Transformers library. We build a sentiment analysis pipeline, I show you the Model Hub, and how you can fine tune your own models.

Get my Free NumPy Handbook: https://www.python-engineer.com/numpy...

✅ Write cleaner code with Sourcery, instant refactoring suggestions in VS Code & PyCharm: https://sourcery.ai/?utm_source=youtu... *

⭐  Join Our Discord : Discord: discord

📓 ML Notebooks available on Patreon:
Patreon: patrickloeber

If you enjoyed this video, please subscribe to the channel:
▶️ : @patloeber

The Huggingface transformers library is probably the most popular NLP library in Python right now, and can be combined directly with PyTorch or TensorFlow. It provides state-of-the-art Natural Language Processing models and has a very clean API that makes it extremely simple to implement powerful NLP pipelines.

Resources:
https://huggingface.co/
https://huggingface.co/models
https://huggingface.co/transformers/c...

PyTorch Course: PyTorch Tutorials - Complete Beginner...
TensorFlow Course: TensorFlow 2 Beginner Course

~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~

🖥️ Website: https://www.python-engineer.com
🐦 Twitter - Twitter: patloeber
✉️ Newsletter - https://www.python-engineer.com/newsl...
📸 Instagram - Instagram: patloeber
🦾 Discord: Discord: discord
▶️  Subscribe: @patloeber

~~~~~~~~~~~~~~ SUPPORT ME  ~~~~~~~~~~~~~~

🅿 Patreon - Patreon: patrickloeber

#Python

Timeline:
00:00 - Introduction
00:43 - Pipeline
09:19 - Model And Tokenizer
15:20 - PyTorch classification
21:55 - Saving And Loading
23:33 - Model Hub
31:30 - Fine Tuning

----------------------------------------------------------------------------------------------------------
* This is an affiliate link. By clicking on it you will not have any additional costs, instead you will support me and my project. Thank you so much for the support! 🙏
3 سال پیش در تاریخ 1400/03/24 منتشر شده است.
113,837 بـار بازدید شده
... بیشتر