Home
:
Book details
:
Book description
Description of
Llm Fine Tune With Custom Data
Published 2/2024 MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz Language: English | Size: 1.96 GB | Duration: 3h 15m Learn how to fine tune GPT 3.5 Turbo models using OpenAI, Gradient platforms with your own datasets What you'll learn Understanding Fine tuning vs training data Fine tune using GPT models, GPT 3.5 Turbo models, Open AI models Preparing, creating, and uploading training and validation datasets Fine tuning using Gradient Platform Create Elon Mush Tweet Generator Build a data extraction fine-tune model Requirements Basic python knowledge Description Overview Section 1: Introduction Lecture 1 What is fine-tuning? Lecture 2 Training vs Fine-tuning Lecture 3 The Foundation models Lecture 4 Why Fine-tune? Lecture 5 Ways to fine-tune a model Lecture 6 Model parameters Section 2: Fine tune using GPT models Lecture 7 Models availability, and use cases Lecture 8 Prepare the sample data Lecture 9 Format the sample data Lecture 10 Token counting function Lecture 11 Check warning and OpenAI cost Lecture 12 Understanding model fine-tuning Lecture 13 Training vs Validation data Lecture 14 Uploading training and validation data to OpenAI Lecture 15 Create a fine tune job Lecture 16 QA using your new model Section 3: Fine tune using gradient platform Lecture 17 Gradient platform - Setting up login Lecture 18 Gradient platform - Interface Lecture 19 What are some of the pre-trained model available? Lecture 20 Create a new model with sample data Lecture 21 What is epochs? Lecture 22 Fine tuning the model and QA Section 4: Elon Musk tweet generator Lecture 23 Prepare the datasets with OpenAI Lecture 24 Create a fine-tune model Lecture 25 Testing the model in OpenAI playground Lecture 26 Elon Musk Tweet Generator Streamlit app Section 5: Data Extraction fine-tune model Lecture 27 Extract any valuable information from raw text Section 6: Congratulations and Thank You! Lecture 28 Your feedback is very valuable!