Fine-tuning Gemini with Google AI Studio Tutorial - [Customize a model for your application]
HTML-код
- Опубликовано: 2 окт 2024
- Learn how to fine-tune the Gemini model using Google AI Studio to enhance its performance for your specific tasks. This tutorial covers dataset preparation, fine-tuning processes, and advanced tuning settings to customize the model to your needs.
SUBSCRIBE for more! 👉 bit.ly/3zlUmiS 👈
Get started with the Gemini API
ai.google.dev/...
👨💻 Ask Me Anything about AI -- Access Exclusive Content ☕
www.skool.com/...
Business Newsletter [FREE] 📰
aitraining.web...
-------------------------------------------------
➤ Follow @webcafeai
• ✈️ 2nd Channel: / @corbinwander
• ✖️ X: x.com/webcafeai
• 🔴 TikTok: / webcafeai
• 🥾 Instagram: / webcafeai
• 🎧 Bräunlich: / braunlich
-------------------------------------------------
Key Takeaways:
✩ Dataset Preparation: Ensure your training dataset is high quality, diverse, and representative of your expected production traffic.
✩ Tuning Process: Fine-tuning involves adjusting the model with example inputs and outputs to teach it desired behaviors or tasks.
✩ Advanced Settings: Optimize the tuning process with settings like epochs, batch size, and learning rate to improve model performance.
▼ Extra Links of Interest:
Fine-tuning with the Gemini API
ai.google.dev/...
🌲 Do You Create Content?
bit.ly/bumpups
⚡ AI Services
webcafesoftwar...
automate everything. 👇
linktr.ee/webcafe
My name is Corbin, an AI developer entrepreneur behind the vision of Webcafe AI. Together we will build digital ecosystems. ☕
How do you access the fine tuned model from API?
💫🙏🎯👊🤙💪🗿🎬🔥🦅☯️ Thank You CB Great Value Add As Usual Sir
Is there a limit to the tokensize of the output? Im thinking about training a model to output json files based on my input to control a 3rd party software but jsons might be kinda big
Clickbait Thumbnail, Gemini flash's finetuning hasn't released yet
how can I use my tuned model in my flutter app ?
still cant find an answer to this
bro... go to new prompt and click get code
@@deepfakes4567 but there aren't "flutter" option there
Did you find how?
In the terms of finetuning, what's the benefit of doing this fine-tuning process opposed to just using vanilla Gemini and prompting it: "For a real estate agency, give me a caption with an emoji and 2 hashtags"? After all, using fine tuning models via the API is typically more expensive, right?
Grrreat content, thank you
how can we use that model url in api
same
go to new prompt and click get code
same here
First Comment
Thanks for sharing 👏🏻
I do the same but I want it use my tuning model on colab but I got this error
403 POST You do not have permission to access tuned model tunedModels.
Can you provide a video for that 😢
I am getting the same error
API keys are not sufficient when u try and use user specific data such as tuned models. You need to configure OAuth credentials
This is easy for simple use cases where the output is always similar in structure. Corbin, have you used AI studio to fine-tune based on unstructured data? IE: inputting data to capture a person’s unique writing style. I have 500 articles and writing examples from wiki pages I've written on software engineering. Each item has a category and a label that I've curated but the copy in the body for each item varies widely. It may be the wrong approach to try to fine-tune based on a persons writing style using AI studio. Maybe, I just need to create embeddings and store them in a vector DB, first. Thoughts?
Thanks Corbin, love the channel!
@@htrbgfdvcxzaefwgrhbntgsca4056 how to do it bro please tell.
Clickbait thumbnail. hit report.