In this video, we are going to see how we can create our own dataset using Augmentoolkit module.
Using the dataset that we would create, we are going to finetune our models.
Now, you can finetune your own models using your own dataset using unsloth and Augmentoolkit.
#owndataset #augmentoolkit
Links:
Augmentoolkit: https://github.com/e-p-armstrong/augmentoolkit?tab=readme-ov-file#rptoolkit
Unsloth: https://unsloth.ai/
Github Unsloth: https://github.com/unslothai/unsloth
Conversation notebook: https://colab.research.google.com/drive/1T5-zKWM_5OD21QHwXHiV9ixTRR7k3iB9?usp=sharing
Normal notebook: https://colab.research.google.com/drive/1hoHFpf7ROqk_oZHzxQdfPW9yvTxnvItq?usp=sharing
CHANNEL LINKS:
🕵️♀️ Join my Patreon for keeping up with the updates: https://www.patreon.com/PromptEngineer975
☕ Buy me a coffee: https://ko-fi.com/promptengineer
📞 Get on a Call with me at $125 Calendly: https://calendly.com/prompt-engineer48/call
💀 GitHub Profile: https://github.com/PromptEngineer48
🔖 Twitter Profile: https://twitter.com/prompt48
00:00 Intro
01:00 Cruz of Dataset Finetuning
3:23 Augmentoolkit Intro
4:51 Cloning the Github code
7:24 Detailed Explanation
8:32 Together AI
12:39 Uploading to Huggingface
13:51 Finetuning Exercises
16:33 Summary and Way Forward
Other videos that you would love:
https://youtu.be/lhQ8ixnYO2Y
https://youtu.be/QTv3DQ1tY6I
https://youtu.be/gcMdzGrDLlw
https://youtu.be/GKr5URJvNDQ