404

Page Not Found

Recent Posts

GPT Instruction Fine-tuning With Keras Members Public

Fine-tuning has become the new training because training large language models (LLMs) from scratch is computationally expensive. It also requires collecting and preparing large datasets which is also time intensive. These resources are only the purview of a few individuals and organizations. Fortunately, there are many open-source LLMs that one

Derrick Mwiti
Derrick Mwiti

How to Detect AI Generated Content With TensorFlow Members Public

With the plethora of open-source language models, it's incredibly difficult to determine if a piece of text is AI generated. However, with a good dataset, you can train a model in TensorFlow to detect if a large language model generated text. It's such an interesting problem

Derrick Mwiti
Derrick Mwiti
TensorFlow

Convolutional Neural Networks in JAX: Ultimate Guide Members Public

JAX is a high performance library that offers accelerated computing through XLA and Just In Time Compilation. It also has handy features that enable you to write one codebase that can be applied to batches of data and run on CPU, GPU, or TPU. However, one of its biggest selling

Derrick Mwiti
Derrick Mwiti
JAX

TensorFlow Tensors(What are Tensors: Understanding the Basics, Creating, and Working with Tensors) Members Public

First off: If you are familiar with NumPy arrays, understanding TensorFlow Tensors will be as easy as first importing TensorFlow as below: import tensorflow as tf print(tf.__version__) # check version # 2.14.0 💡The examples in this article use TensorFlow v2.x, so concepts deprecated and or that were

Brian Mutea
Brian Mutea

Implementing Transformer decoder for text generation in Keras and TensorFlow Members Public

The recent wave of generative language models is the culmination of years of research starting with the seminal "Attention is All You Need" paper. The paper introduced the Transformer architecture that would later be used as the backbone for numerous language models. These text generation language models are

Derrick Mwiti
Derrick Mwiti
TensorFlow

Text Classification With BERT and KerasNLP Members Public

BERT is a popular Masked Language Model. Some words are hidden from the model and trained to predict them. The model is bidirectional, meaning it has access to the words to the left and right, making it a good choice for tasks such as text classification. Training BERT can quickly

Derrick Mwiti
Derrick Mwiti
TensorFlow