|  

Udemy - Mastering LLM Alignment and Preference Optimization Llama3 LLM



Size :263.1 MB
Peers : Seeders : 0      Leechers : 0
Added : 5 months ago » by freecoursewb » in Other
Language : English
Last Updated :5 months ago
Info_Hash :CB054423C971F4153577B76EEFA572A705BC46B0

Torrent File Contents

Udemy - Mastering LLM Alignment and Preference Optimization Llama3 LLM
  Get Bonus Downloads Here.url
  -  182 Bytes

  ~Get Your Files Here !/1. Introduction.mp4
  -  59.77 MB

  ~Get Your Files Here !/2. Dataset Creation.mp4
  -  72.49 MB

  ~Get Your Files Here !/3. Model Creation and Initial Evaluation.mp4
  -  33.92 MB

  ~Get Your Files Here !/4. Training with Direct Preference Optimization.mp4
  -  30.82 MB

  ~Get Your Files Here !/5. Training with Direct Preference Optimization - Part 2.mp4
  -  42.03 MB

  ~Get Your Files Here !/6. Final Model Evaluation.mp4
  -  24.11 MB

  ~Get Your Files Here !/6.1 trainer.py
  -  3.74 KB

  ~Get Your Files Here !/Bonus Resources.txt
  -  386 Bytes



Torrent Description

Mastering LLM Alignment & Preference Optimization Llama3 LLM

https://DevCourseWeb.com

Published 5/2024
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz, 2 Ch
Language: English | Duration: 39m | Size: 265 MB

Mastering Direct Preference Optimization: Practical Techniques with LLaMA3, Hugging Face, and Advanced Language Models

What you'll learn
Learn how to use direct preference optimization training.
Use HuggingFace TRL Library with Llama3 8B for direct preference training
Learn how to train on your own data with direct preference optimization
Learn the science behind direct preference optimization and optimizing large language models.

Requirements
A premium Google Colab account, basic python knowledge.