Prompt Engineering
Introduction In just five days, ChatGPT managed to exceed one million users, a feat that took Netflix 3.5 years, Facebook…
“Text-to-Color” from Scratch with CLIP, PyTorch, and Hugging Face Spaces
Example input and output from the Gradio app built using the Text to Color model. Moving from left to right,…
Using CLIP and Gradio to assess similarity between text prompts and ranges of colors
Link to Colab notebook Hugging Face Space Intro OpenAI’s CLIP model and related techniques have taken the field of machine…
4 Techniques To Tackle Overfitting In Deep Neural Networks
Image Created By Author Using Canva A neural network is a combination of different neurons, layers, weights, and biases. The…
How To Train Your Deep Learning Models Faster
Photo by Marc-Olivier Jodoin on Unsplash Deep learning is a subset of machine learning that utilizes neural networks in “deep” architectures, or…
How to 10x Throughput When Serving Hugging Face Models Without a GPU
By optimising how a model is served, we serve over 100 predictions per second with a simply Python API using CPU inference
Debugging Classifiers with Confusion Matrices
A confusion matrix can provide us with a more representative view of our classifier’s performance, including which specific instances it is having trouble classifying.
