Yapay zekadan makale özeti
- Kısa
- Ayrıntılı
- Bu video, bir eğitim içeriği olup, izleyicilere Python kullanarak LLM'leri (Large Language Models) yerel bilgisayarda nasıl çalıştırabileceklerini adım adım göstermektedir.
- Video, LLM'leri çalıştırmak için gerekli olan ALLA (All-Language Models) platformunun kurulumundan başlayarak, LLM 3.1 modelinin indirilmesi, Python sanal ortamının oluşturulması ve LLM 3.1'i Python ile çağırmak için gerekli Python kodunun yazılması sürecini kapsamaktadır. Eğitmen, "diffraction of light" sorusu üzerinden LLM'in nasıl çalıştığını göstermekte ve oluşturulan yanıtın bir metin dosyasına nasıl kaydedileceğini açıklamaktadır. Video, LLM'leri yerel bilgisayarda kullanmak isteyenler için kapsamlı bir rehber niteliğindedir.
- Introduction to ALM and LLM
- The video explains how to run LLM (Large Language Model) 3.1 using Python on Windows and a local computer.
- ALM is an interface and platform for running different LLMs on local computers.
- LLM 3.1 is the most popular and updated LLM, and can be run using the Python library.
- 01:37Setting Up ALM
- The first step is to install ALM and download LLM 3.1 from the ALM website.
- Create a workspace folder, create a Python virtual environment, and install the ALM Python library.
- Write a Python script to call LLM 3.1 and save the response text file.
- 03:00Installing ALM
- Download the ALM installation file from the website and execute it.
- The installation process creates a folder in the user's app data folder.
- ALM is running in the system background, and you can check it by searching for ALM in command prompt.
- 04:59Downloading LLM 3.1
- Go to the ALM website and select LLM 3.1 from the server choices.
- Choose the LLM size (20 billion parameters or 4 milyar parameters) and download the installation command.
- The installation process downloads about 2.7 gigabytes of data, which takes some time.
- 06:04Running LLM
- Execute the installation command in the terminal to download and install LLM 3.1.
- After installation, you can run LLM from the terminal.
- The video demonstrates generating a response about "diffraction of light" using LLM 3.1.
- 07:43Creating Python Virtual Environment
- Create a folder named "codes" and inside it, create another folder named "lam" as the base folder for the project.
- Use the Python command to create a virtual environment named "alm".
- Activate the virtual environment and install the ALM Python library.
- 09:28Writing Python Script
- Use Visual Studio Code to create a new Python file named "test.py".
- Copy the Python script provided in the video and paste it into the file.
- The script calls ALM, selects the LLM, asks a question, and saves the response text file.
- 12:05Running Python Script
- Run the Python script using the virtual environment.
- The script generates a response about "diffraction of light" and saves it to a text file.
- The generated response can be used in reports or other documents.