Skip to main content
grasp.study
Back to course
Log in
Get started
Someone wanted to learn this too, so Grasp built them a personal learning path.
Create your own
Llama Local Models and Training
ยท
Module 1
Local LLM Concepts and Workflow
1
Key Roles in a Local LLM System: Pretraining, Inference, Prompting, RAG, and Fine-Tuning
Distinguish pretraining, inference, prompt engineering, retrieval-augmented generation, and fine-tuning by the role each plays in a local LLM system.
2
How Tokens, Parameters, Context, and Next-Token Prediction Shape Language Models
Explain how tokens, parameters, context length, and next-token prediction determine a language model's behavior.
3
Exploring Llama Tokenization and Text Reconstruction
Inspect how a Llama tokenizer converts text to token IDs and reconstructs the text.
4
Evaluating Llama Models for Task and Deployment Fit
Use a model card and license to determine whether a Llama-family model fits a specified task and deployment scenario.
Previous module
Next module
PyTorch Foundations for Language Models