LLM - Run locally using OLlama

What is ollama?
  1. Ollama is a simple tool that lets you download and run large language models on your own computer, without needing a powerful server.
  2. It compiles C++ code versions of LLMs directly on the machine.
What is installed?
  1. PaLM 2 - Trained on a significantly larger dataset than previous models, giving it a broader understanding of the world.
  2. Note, Google created smaller, more efficient PaLM 2 models tailored for specific applications, like Bard (the chatbot) and Vertex AI.
How do I install ollama?
  1. Navigate to https://ollama.com/download, and download the correct version
  2. Run setup program, and follow prompts
  3. Run ollama from the command prompt, or powershell "ollama run gemma3"
  4. Enter "I am trying to learn French. I am a complete beginner. Please have a conversation with me to teach me french"
  5. We are using a free open source project, to unlock paid features in real applications

Different version of models can be seen from Ollama.com/library

  1. Good to experiment with them and find what use cases they best support for your problem
  2. This is a critical skill for an LLM engineer
Key takeaway
  • Demonstrated use case: Building a free, local AI language tutor (Spanish/French), replicating commercial app features at no cost, showcasing rapid creation of commercially viable AI solutions. This immediate application highlights the commercial value of open-source LLMs.

Strategic Implications & High-Level Insights

  • Democratization of AI Capabilities: Deploying advanced LLMs locally, without cloud dependencies or licensing fees, lowers barriers for rapid prototyping and internal innovation.

  • Cost Efficiency: Open-source models can replace paid AI services, enabling organizations to internalize capabilities and reduce recurring SaaS costs.

  • Model Selection as a Core Competency: Early focus on experimenting with multiple models (Meta’s Llama, Google’s Jammer, Alibaba’s Quen, Microsoft’s Phi) to identify the best fit for specific tasks—a critical skill for an LLM engineer crucial for maximizing ROI and performance in enterprise AI deployments.

  • Performance Considerations: Hardware architecture (e.g., Apple M1 vs. PC emulation) significantly affects LLM performance, guiding infrastructure investment decisions, as larger models may run slower on certain hardware.



 

Comments

Post a Comment

Popular posts from this blog

Feature: Audit log for one login, and identity service

Image
Customer (Product) Page High-Level System Design Diagram (PlantUML) Sequence Diagram: Audit Event Ingestion Sequence Diagram: Orchestration Event For a High-Level System (Component) Diagram The queue is implemented as message_queue (generic), and the audit log service consumes from it, writing to a dedicated audit_log table. The logging service also consumes from the same message_queue and writes to log_store. Orchestration/other services use the same queue. Summary Table: What Writes Where Event Type Goes Into Consumed By Final Storage audit message_queue Audit Log Service audit_log table log message_queue Logging Service log_store table doc_uploaded message_queue Orchestration Worker (business DB, or triggers next event) ocr_ready message_queue Notification Worker, etc. (notification log, etc.)  Core Tables message_queue – universal event bus (temp buffer) audit_log – immutable audit/compliance events log_store – application logs (op...
Read more

Getting started - Build your data science lab environment

This guide explains how to set up a complete data science environment for the udemy program. A proper setup ensures compatibility and avoids recurring environment issues.  1. Overview Goal : Create a full-featured environment with sufficient resources for all course exercises. Recommendation : Use Anaconda for the most reliable setup. Alternative : Use a Python virtual environment with pip if Anaconda isn’t working. 2. Setup Options Primary (Recommended) Create a dedicated Anaconda environment (isolated, compatible). Alternative Use a standard Python virtualenv + pip (faster but less reliable). 3. Windows Setup Steps Clone Course Repository git clone https://github.com/ed-donner/llm_engineering/ Follow the repository’s README.md instructions for additional setup details. Create Anaconda Environment Inside the llm_engineering folder: conda env create -f environment.yml ⏳ This may take several minutes. Activate the environment: conda activate llms Deactivat...
Read more

QA - Run #1 - Results

Image
# QA Report for Tag QA_July2025_A - **Tag/Commit:** QA_July2025_A (`f32abc1`) - **Date:** 2025-08-01 - **QA Outcomes:** All tests passed except for file upload (see below)... - **Environment:** Windows 10, Python 3.12, requirements.txt as of tag - **Notes:** See log for detailed results. ## Issue Found - **Step:** - **Bug:** - **Log excerpt:** - **Screenshot:** For this QA run, we begin with pristine state by: Stop all services Delete logs.db, and jobs.db Delete all files in doc_store folder Start all services Test, you should see no data on index page, and query should result in no data found error Next, go ahead and upload new1.txt, and after that new2.txt Issue the query: "can you summarize all of the todo items you can find, seperating each one on a single line, with due date first, then title, and description with any details you can augment" Expected Answer: - August 1, 2025: Respond to Amira and discuss weekend plans - August 3, 2025: Go to Somesh class and finish ta...
Read more