Beginner30 min
Getting Started with LLaMA 3
Learn how to set up and run LLaMA 3 models locally on your machine
Last updated: 2025-01-15
Prerequisites
- Basic Python knowledge
- GPU with 8GB+ VRAM
- Linux or macOS
1. Install Dependencies
First, install the required Python packages and dependencies.
pip install transformers torch accelerate2. Download the Model
Download LLaMA 3 from Hugging Face.
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B")3. Run Inference
Generate text using the model.
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))