This blog post delves into the initial fine-tuning process for large language models (LLMs) for multi-turn conversations and their deployment on Text Generation Inference (TGI) servers. It covers topics such as use cases, data formats, training data preparation, server setup, and evaluation frameworks. The goal is to guide readers through the process of fine-tuning and deploying LLMs.
How do you handle access to the local filesystem data with Podman Desktop on macOS?
This blog post explores managing local filesystem access with Podman Desktop on macOS. It discusses two options: mapping an existing local folder as a volume to the container, and creating a local Podman volume and accessing data inside the container. Detailed steps for both approaches are provided, addressing potential access rights issues.
Easy migration from org.json to Gson
This blog post discusses how to migrate from org.json to Gson. It provides code examples for both libraries and concludes that the migration requires minimal changes.
How to create a watsonx.ai REST client in Spring Boot?
This blog post demonstrates the Java Spring Boot implementation to invoke a watsonx.ai endpoint. It outlines the classes and steps involved, including building and sending requests, handling prompts, and extracting answers. The post also provides sample code for invoking the endpoint and using RestTemplate. Overall, it offers a comprehensive guide on utilizing watsonx.ai in a Spring Boot application.
Create an IBM Cloud IAM access token in your Spring Boot Java application
This blog post provides an example of obtaining an IBM Cloud access token using the IBM Cloud IAM REST API and Spring Boot. It includes a Java RestClient implementation for getting the access token and a REST endpoint invocation in a sample application.
Get started with Spring Boot Java application development using Maven, add Swagger UI and an initial basic authentication
This blog post provides a customized extract of the "Spring Boot Quickstart" to start a Spring Boot Java application using Maven, Swagger UI, and initial basic authentication without source code changes. It covers creating a "Hello World" WebService, adding a Swagger UI server, implementing initial basic authentication, and additional resources.
CheatSheet: How to set up Java and Maven on macOS
This blog post provides a list of links to resources for setting up a Java development environment on MacOS.
Getting started with Text Generation Inference (TGI) using a container to serve your LLM model
This blog post outlines a bash automation for setting up and testing Text Generation Inference (TGI) using a container. It provides instructions for creating a Python test client, starting the TGI server, and troubleshooting common issues. The post emphasizes the benefits of using containers and references the Hugging Face and Nvidia technologies.
CheatSheet: How to add users to your watsonx project?
This cheat sheet provides a two-step guide for adding users to your watsonx project in IBM Cloud.
CheatSheet: Configure the Block Storage usage in Virtual Server Instances on IBM Cloud
This post introduces the use of Block Storage in Virtual Server Instances, particularly in relation to GPUs. It covers the process of mounting and configuring block storage, along with creating, formatting, and mounting the disk. It also provides steps for permanently mounting the storage and attaching existing block storage to a new virtual service instance machine.