Fine-Tune Phi- 3 for Free Google Colab with Unsloth
Unleash Phi 3's power for FREE! This video guides you through fine-tuning it on Google Collab for specific tasks for free using Unsloth and open source dataset from Hugging face
Support Me on Petron ⚡: / codewello
00:00 - Intro
00:24 - Benchmark for Phi - 3
01:10 - Test Phi-3 Medium
03:11 - Phi-3 Fine Tuning Requirements
04:00 - Unsloth
04:29 - Code Setup
05:03 - What Unsloth do for us
06:01 - LoRa Adapters
06:12 - Dataset Format
08:30 - Train Phi-3
09:29 - Inference
10:19 - Saving and Loading fine tuned model
12:07 - Unsloth Speed
Unsloth :https://github.com/unslothai/unsloth
Phi-3 Paper: https://arxiv.org/abs/2404.14219
Phi-3 Model used: https://huggingface.co/unsloth/Phi-3-...
_______________________________________________________________
🤖 Open AI Template Alima : https://codewello.gumroad.com/l/kjlzw
💷 50% Discount Code : A2LH6LZ
👉 Linkedin : / hossam-eldin
_______________________________________________________________
📕 Mastering Yolo V8 Object Detection : • Mastering YOLO V8: Object Detection a...
📙 Supervision : • Supervision with Yolo V8 : Video Trac...
📗 Mastering Yolo NAS : • Mastering YOLO NAS: Object Detection
🧑🏻💻 Build Ai Assistant : • OpenAI Assistant: From Zero to Deploy...
#phi3 #finetune #microsoft #ai #llms #opensource #free