This video is sponsored by Gradient.ai, check them out here: gradient.1stcollab.com/engine...
In this video, we will learn how to fine-tune Mistral-7B on your own data.We will look at data preparation and preprocessing for getting the best results.
Want to Follow:
🦾 Discord: / discord
▶️️ Subscribe: www.youtube.com/@engineerprom...
Want to Support:
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Support my work on Patreon: / promptengineering
Need Help?
📧 Business Contact: engineerprompt@gmail.com
💼Consulting: calendly.com/engineerprompt/c...
Join this channel to get access to perks:
/ @engineerprompt
LINKS:
Google Colab: tinyurl.com/5n7jkx4z
Gradient: gradient.ai/
LoRA: huggingface.co/docs/peft/conc...
TIMESTAMPS:
[00:00] Introduction
[01:06] Understanding and Formatting the Dataset
[03:24] Filtering and Structuring the Dataset
[05:45] Transforming the Dataset to single column
[10:00] Preparing for Model Training - Mistral-7B Fine tuning
[14:46] Understanding and Applying LoRa for Training
[18:36] Running the Training Process
[20:11] Storing and Testing the Trained Model
[21:12] Recap and Conclusion
All Interesting Videos:
Everything LangChain: • LangChain
Everything LLM: • Large Language Models
Everything Midjourney: • MidJourney Tutorials
AI Image Generation: • AI Image Generation Tu...
Негізгі бет Ғылым және технология Mistral: Easiest Way to Fine-Tune on Custom Data
Пікірлер: 59