Today is my 25th anniverary at IBM. Times flies when you’re having fun. I have the pleasure to work with so many nice and smart people. Thank you to my colleagues, to my managers, to my mentors, c...
Fine-tuning LLMs with Apple MLX locally
MLX is a framework for machine learning with Apple silicon from Apple Research. This post describes how to fine-tune a 7b LLM locally in less than 10 minutes on a MacBook Pro M3. MLX is designe...
How to stay up to Date with AI News
Recently several people have asked me how I follow AI news. Below are some great resources. YouTube I like watching videos during my lunch break workouts. I can highly recommend the following cha...
Fine-tuning LLMs locally with Apple Silicon
With recent MacBook Pro machines and frameworks like MLX and llama.cpp fine-tuning of Large Language Models can be done with local GPUs. This post describes how to use InstructLab which provides an...
Running fine-tuned LLM Models on watsonx.ai
Watsonx.ai is IBM’s AI platform built for business. It is provided as SaaS and as software which can be deployed on multiple clouds and on-premises. This post describes how to deploy custom fine-tu...
Understanding the Watsonx.ai API
Watsonx.ai is IBM’s enterprise studio for AI builders to train, validate, tune and deploy Large Language Models. It comes with multiple open source and IBM LLMs which can be accessed via REST API. ...
Running Mistral on CPU via llama.cpp
Via quantization LLMs can run faster and on smaller hardware. This post describes how to run Mistral 7b on an older MacBook Pro without GPU. Llama.cpp is an inference stack implemented in C/C++ to...
Generating synthetic Data with Mixtral
Fine-tuning and aligning language models to follow instructions requires high quality data and a large quantity of data. IBM published a paper that describes how synthetic data can be generated wit...
Mixtral Agents with Tools for Multi-turn Conversations
Larger Large Language Models like ChatGPT can be prompted to behave as agents for specific use cases. They can return output in certain formats, and they can return instructions to invoke code. Thi...
Deploying LLMs via Hugging Face on IBM Cloud
With the Text Generation Inference toolkit from Hugging Face Large Language Models can be hosted efficiently. This post describes how to run open-source models or fine-tuned models on IBM Cloud. T...