Navigate Select ESC Close

EASIEST Way to Fine-Tune LLAMA-3.2 and Run it in Ollama

2024-09-29 Science & Technology
100.8k
1.9k
62
Prompt Engineering
Prompt Engineering
241.0k subscribers

Unlock all features

FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.

Description

Meta recently released Llama 3.2, and this video demonstrates how to fine-tune the 3 billion parameter instruct model using Unsloth and run it locally with Olama. By preparing the FindTom100K dataset, adjusting prompt templates, and adding LoRA adapters, the tutorial covers efficient fine-tuning and conversion of the model into GGUF format for local deployment. This enables users to run custom fine-tuned Llama 3.2 models on their own devices, leveraging powerful AI capabilities without relying on cloud resources. LINKS: Colab: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing https://www.llama.com/ Dataset: https://huggingface.co/datasets/mlabonne/FineTome-100k Ollama madelfile: https://github.com/ollama/ollama/blob/main/docs/modelfile.md 💻 RAG Beyond Basics Course: https://prompt-s-site.thinkific.com/courses/rag Let's Connect: 🦾 Discord: https://discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: https://ko-fi.com/promptengineering |🔴 Patreon: https://www.patreon.com/PromptEngineering 💼Consulting: https://calendly.com/engineerprompt/consulting-call 📧 Business Contact: [email protected] Become Member: http://tinyurl.com/y5h28s6h 💻 Pre-configured localGPT VM: https://bit.ly/localGPT (use Code: PromptEngineering for 50% off). Signup for Newsletter, localgpt: https://tally.so/r/3y9bb0 00:00 Introduction to Llama 3.2 Release 00:40 Overview of Llama 3.2 Models 01:42 Fine-Tuning Llama 3.2 with Unsloth 01:58 Preparing the Dataset for Fine-Tuning 02:34 Setting Up the Fine-Tuning Environment 03:32 Configuring the Fine-Tuning Parameters 07:59 Training the Model 12:31 Running the Fine-Tuned Model Locally 16:39 Conclusion and Future Videos All Interesting Videos: Everything LangChain: https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr Everything LLM: https://youtube.com/playlist?list=PLVEEucA9MYhNF5-zeb4Iw2Nl1OKTH-Txw Everything Midjourney: https://youtube.com/playlist?list=PLVEEucA9MYhMdrdHZtFeEebl20LPkaSmw AI Image Generation: https://youtube.com/playlist?list=PLVEEucA9MYhPVgYazU5hx6emMXtargd4z

Top Comments (10)

@lulzkiller666 2024-10-09

Nice video. Could you please make a video on how to train it on "own" content. Lets say, i have the complete API documentation for an APP, i want to train it on this API documentation so that it can help me code faster with the correct API's. That would be awesome

16
@gramnegrod 2024-09-29

Great video. You make it look so easy! I’m really looking forward to the vision based rag. I’m hoping good vision models with vision rag will open up a lot of creative use cases.

3 1 replies
@ankansaha3260 2025-03-21

Bro where is the tutorial for fine-tuning LLAMA-3.2 for the vision task?? I'm eagerly waiting for that one.

1
@iamtguy 2024-11-15

Great tutorial 🔥

0
@rezcan 2024-10-16

Great video, thanks can you make a video to show how to fine tune Llama 3.2 90B vision model?

0
@maxwelikow9119 2024-11-29

Cool video! Do you have an idea how to fine-tune the llama3.2-vision models?

0
@robertjalanda 2024-09-30

great video waiting for vision support

0
@lysanderAI 2024-10-25

Could you do a video of finetuning using axolotl + unsloth

0
@vb6code 2025-03-28

Thanks for sharing

0
@aganithshanbhag 2025-01-16

Thank you, this was a huge help!

0

Unlock the Data Inside
Turn Videos into Knowledge

  • Get FREE 10/day: transcripts, summaries, chats
  • Chat with videos, export text & PDF
  • $1 free API credit for RAG, chatbots & research

Free forever plan • All features unlocked

App screenshot