LLAMA-3.1 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌

Опубликовано: 30 Июль 2024
на канале: Prompt Engineering

39,325

868

Learn how to efficiently fine-tuning the Llama 3.1 model using Unsloth, LoRa, and QLoRa techniques.

LINKS:
Colab: https://tinyurl.com/bdzxhy5n
Unsloth: https://unsloth.ai/blog/llama3-1
Huggingface blog: https://huggingface.co/blog/mlabonne/...
Unsloth UI: https://tinyurl.com/24shjemu
Dataset: https://tinyurl.com/2jh5ajr3

💻 RAG Beyond Basics Course:
https://prompt-s-site.thinkific.com/c...

Let's Connect:
🦾 Discord:   / discord
☕ Buy me a Coffee: https://ko-fi.com/promptengineering
|🔴 Patreon:   / promptengineering
💼Consulting: https://calendly.com/engineerprompt/c...
📧 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

TIMESTAMPS:
00:00 Introduction to Open Weight Models
00:26 Fine-Tuning Lama 3 with UnSloth
00:46 Stages of Model Training
02:21 Supervised Fine-Tuning Techniques
04:43 Setting Up the Training Environment
06:07 Understanding LoRa and QLoRa
09:15 Data Preparation for Fine-Tuning
10:51 Training and Inference
12:46 Saving and Loading Models
13:40 UnSloth's Chat UI Demo
14:44 Conclusion and Next Steps

All Interesting Videos:
Everything LangChain:    • LangChain

Everything LLM:    • Large Language Models

Everything Midjourney:    • MidJourney Tutorials

AI Image Generation:    • AI Image Generation Tutorials

Смотрите видео LLAMA-3.1 🦙: EASIET WAY To FINE-TUNE ON YOUR DATA 🙌 онлайн без регистрации, длительностью часов минут секунд в хорошем качестве. Это видео добавил пользователь Prompt Engineering 30 Июль 2024, не забудьте поделиться им ссылкой с друзьями и знакомыми, на нашем сайте его посмотрели 39,325 раз и оно понравилось 868 людям.