From the course: Applied AI: Getting Started with Hugging Face Transformers
Join today to access over 24,400 courses taught by industry experts.
Training with Hugging Face
From the course: Applied AI: Getting Started with Hugging Face Transformers
Training with Hugging Face
- [Instructor] The pre-built model checkpoints and pipelines in hugging face can be used out of the box for specific NLP tasks. However, sometimes it may be necessary to train a custom model. What does it take to build a custom model using hugging face artifacts as a baseline. Training with hugging face involves using the model checkpoints and customizing them. Transfer learning is used to customize the model. During customization, the model architecture can be enhanced. A smaller dataset specific to the use case can be used for training. It is also possible to freeze the weights of the original checkpoint and add new layers specific to the use case. During training, multiple artifacts from hugging face can be reused. This includes tokenizers, foundation models as well as datasets. How do we train a custom model for say, a sentiment analysis use case? We first start with a training text corpus. We can bring in our…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.
