I want to share my experience in the cloud, AI, and agents development areas.
IBM Granite for Code models on Hugging Face are beneficial for developers, allowing seamless integration with VS Code. They support 116 programming languages and are available under an Apache 2.0 license.
This blog post examines the Confusion Matrix as a metric for evaluating the performance of large language models (LLMs) in classification tasks, especially legal document analysis. It discusses the calculation of key classification metrics like Accuracy, Precision, Recall, and F1 score, emphasizing the challenges of using a broadly defined Ground Truth.
The blog post introduces InstructLab, a project by IBM and Red Hat, outlining the fine-tuning process of the model "MODELS/MERLINITE-7B-LAB-Q4_K_M.GGUF." This involves data preparation, model training, testing, and conversion, finally serving the model to verify its accuracy, by using a personal musician example.
The popularity of llama.cpp and optimized GGUF format for models is growing. This post outlines steps to run "Phi-3-Small-128K-Instruct" in GGUF format with llama.cpp on an IBM Cloud VSI with GPUs and Ubuntu 22.04. It covers VSI setup, CUDA toolkit, compilation, Python environment, model usage, and additional resources.
This post covers to ensure you set the virtual environment for Python in VS Code using venv. It details creating and activating a Python venv, and ensuring it’s used in VS Code environments. The steps include opening the VS Code command palette, selecting an interpreter, and navigating to the pyvenv.cfg file.
Thomas Suedbroecker's Blog 