Unfolding the universe of possibilities..

Navigating the waves of the web ocean

How ChatGPT is Transforming the Way We Teach Software Development

Learning to code when AI assistants already master the skill Continue reading on Towards Data Science »

Fine-tune a Mistral-7b model with Direct Preference Optimization

Boost the performance of your supervised fine-tuned models Image by author Pre-trained Large Language Models (LLMs) can only perform next-token prediction, making them unable to answer questions. This is why these base models are then fine-tuned on pairs of instructions and

Memory-Efficient Embeddings

Creating smaller models with a new kind of embedding layer Continue reading on Towards Data Science »

How to Detect Hallucinations in LLMs

Teaching Chatbots to Say “I Don’t Know” Continue reading on Towards Data Science »