Learn how to prepare fine-tuning datasets using open source large language models in this 15-minute video tutorial. Explore techniques for Q&A dataset preparation using Llama 2 70B and chat-ui. Discover how to set up a Llama 2 API for the 70B model and utilize it to create a Q&A dataset suitable for fine-tuning. Gain valuable pro tips for dataset preparation and access a GitHub repository containing data preparation scripts. Follow along as the tutorial covers accessing resources, implementing preparation techniques, and optimizing your approach to fine-tuning datasets for large language models.
Preparing Fine-tuning Datasets with Open Source LLMs
Overview
Syllabus
Preparing data for fine-tuning
Video overview
Accessing the GitHub Repo w/ data preparation scripts
Q&A Dataset preparation using Llama 2 70B and chat-ui
How to set up a Llama 2 API for 70B
Using a Llama 2 API to prepare a Q&A dataset for fine-tuning
Pro tips for preparing fine-tuning datasets
Taught by
Trelis Research
Related Courses
-
2025 Fine Tuning LLM with Hugging Face Transformers for NLP
-
Embeddings vs Fine-Tuning - Supervised Fine-tuning - Part 2
-
H2O ai Large Language Models (LLMs) - Level 2
-
Chat Fine-Tuning for LLMs - Instruction Format, Datasets, and Implementation
-
Fine-Tuning LLM Models - Generative AI Course
-
Pretraining LLMs
