Skip navigation
🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with .
0:00 / 0:48

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with .

Eric Ciarla (hiring)

@ericciarla16K followers

Visit on X
291 likesDownloadOriginal post

28,794 views

🔥 We fine-tuned Gemma 3 using Unsloth AI on a custom instruction dataset scraped and built with . The model is now able to answer questions about OpenAI Agents SDK documentation. Check out the demo below👇

6 Comments

Comments from the original post on X (Twitter)

  • Eric Ciarla (hiring)'s profile picture

    @ericciarla

    See the breakdown of the fine-tuning process on our blog and get access to the full code here:

    15 likes

  • Etherspot 🐞's profile picture

    @etherspot

    Want to build a Web3 app without all the overhead costs? Try TransactionKit, a React toolkit that makes building dApps easy. Integrate cutting-edge account abstraction features in just a few clicks. Try it today 👇

    23,365 likes

  • Unsloth AI's profile picture

    @UnslothAI

    @firecrawl_dev @OpenAI Super cool guys! 🦥🔥

    9 likes

  • Mag Mario Jembrih's profile picture

    @Mag_Jembrih

    @UnslothAI @firecrawl_dev @OpenAI Can you fine tune it similarly on local docs like pdfs or books in pdf up to 1k pages or wouldn’t you use it for that

  • Clyde's profile picture

    @clyders3

    @UnslothAI @firecrawl_dev @OpenAI Does that mean I can use it in cursor and it not wreck everything again?

  • Arsen Ibragimov's profile picture

    @iamarsibragimov

    @UnslothAI @firecrawl_dev @OpenAI Check out the demo below.