Loading video...

Video Failed to Load

Go Home

Fine-tune FunctionGemma to resolve tool selection ambiguity and build more accurate agentic workflows. The FunctionGemma Tuning Lab lets you train on your own dataset and test natural language to software actions without writing code or managing infrastructure.

googleaidevs's profile picture

Google AI Developers

97,989 subscribers

20,634 views • 5 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing Lab: A full-stack platform for training your own agentic models Build, evaluate and train on your own environments at scale without managing the underlying infrastructure. Giving everyone their own frontier AI lab.
1:23

Introducing Lab: A full-stack platform for training your own agentic models Build, evaluate and train on your own environments at scale without managing the underlying infrastructure. Giving everyone their own frontier AI lab.

Prime Intellect

3,112,755 views • 4 months ago

FunctionGemma 270M brings powerful agentic capabilities directly to edge devices📱 This video shows how fine-tuning this lightweight model to translate natural language into actionable system commands, can be run entirely on-device for lower latency and better privacy.
5:02

FunctionGemma 270M brings powerful agentic capabilities directly to edge devices📱 This video shows how fine-tuning this lightweight model to translate natural language into actionable system commands, can be run entirely on-device for lower latency and better privacy.

Google AI Developers

26,471 views • 6 months ago

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!
0:46

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source with 50k stars!

Avi Chawla

557,355 views • 1 year ago

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟
0:46

Fine-tune 100+ LLMs directly from a UI! LLaMA-Factory lets you train and fine-tune open-source LLMs and VLMs without writing any code. Supports 100+ models, multimodal fine-tuning, PPO, DPO, experiment tracking, and much more! 100% open-source, 51k+ stars 🌟

Akshay 🚀

60,627 views • 1 year ago

Build fully offline mobile assistants with FunctionGemma 270M. This demo parses natural language commands like “Create a calendar event for lunch tomorrow” or “Add to contacts” to execute OS actions directly on-device.
0:27

Build fully offline mobile assistants with FunctionGemma 270M. This demo parses natural language commands like “Create a calendar event for lunch tomorrow” or “Add to contacts” to execute OS actions directly on-device.

Google AI Developers

86,491 views • 6 months ago

Learn how to fine-tune FunctionGemma on TPUs in a Colaboratory notebook. This guide uses Tunix, a lightweight JAX library, to streamline post-training your LLM🧵👇
10:08

Learn how to fine-tune FunctionGemma on TPUs in a Colaboratory notebook. This guide uses Tunix, a lightweight JAX library, to streamline post-training your LLM🧵👇

Google AI Developers

20,706 views • 3 months ago

Introducing Workflows—a visual builder that lets you program Stripe and create custom flows without writing code. Get started:
0:45

Introducing Workflows—a visual builder that lets you program Stripe and create custom flows without writing code. Get started:

Ben

17,251 views • 1 year ago

The trades can build anything... except the software they run on. That changes today. We've raised $9.2M to build Dalton Mills. Software has spent its whole history getting closer to the people who do the work. First, the system of record. Software you stored your business in. Then, the agentic era. Software that did the work for you. Now, the bespoke era. Agentic software you build yourself, without code. Each era closed the gap and this one closes it for good. Software can finally work around your business, instead of you bending your business to make it fit. You ran on software made for everyone… never for you. That's over. Welcome to Dalton Mills. Let the builders build!
2:14

The trades can build anything... except the software they run on. That changes today. We've raised $9.2M to build Dalton Mills. Software has spent its whole history getting closer to the people who do the work. First, the system of record. Software you stored your business in. Then, the agentic era. Software that did the work for you. Now, the bespoke era. Agentic software you build yourself, without code. Each era closed the gap and this one closes it for good. Software can finally work around your business, instead of you bending your business to make it fit. You ran on software made for everyone… never for you. That's over. Welcome to Dalton Mills. Let the builders build!

Todd Saunders

74,731 views • 1 month ago

Mobile Actions and Tiny Garden are available out-of-the-box in the Google AI Edge Gallery app, now on both Android and iOS. Benchmark the model performance directly in the app. Discover how you can use FunctionGemma (270M) and LiteRT-LM to build private, high-performance local assistants:
0:21

Mobile Actions and Tiny Garden are available out-of-the-box in the Google AI Edge Gallery app, now on both Android and iOS. Benchmark the model performance directly in the app. Discover how you can use FunctionGemma (270M) and LiteRT-LM to build private, high-performance local assistants:

Google for Developers

58,971 views • 4 months ago

Writing code to automate your repo? Great. Writing Markdown to do it? Pretty sick. GitHub Agentic Workflows: now in technical preview.
1:06

Writing code to automate your repo? Great. Writing Markdown to do it? Pretty sick. GitHub Agentic Workflows: now in technical preview.

GitHub

40,905 views • 3 months ago

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️
3:17

NEW: Google releases FunctionGemma, a lightweight (270M), open foundation model built for creating specialized function calling models! 🤯 To test it out, I built a small game: use natural language to solve fun physics simulation puzzles, running 100% locally in your browser! 🕹️

Xenova

58,150 views • 6 months ago

Big update. Today, we're introducing Automations. This is different from old-school marketing automation tools because it allows you to build workflows via... • Drag-and-drop editor • Using AI and natural language • Actual code using Claude Code, Cursor, or Codex
2:09

Big update. Today, we're introducing Automations. This is different from old-school marketing automation tools because it allows you to build workflows via... • Drag-and-drop editor • Using AI and natural language • Actual code using Claude Code, Cursor, or Codex

Zeno Rocha

115,724 views • 2 months ago

An AI assistant for Google Earth Engine is now available in QGIS! You can explore and visualize any dataset from the 80+ PB Earth Engine Data Catalog using natural language, and run scalable geospatial analysis on demand without writing code. Every interaction automatically generates reusable code, making it easy to reproduce results, customize workflows, and transition from no-code to full scripting when needed. Upgrade the plugin to get started and bring AI-powered geospatial analytics directly into your QGIS workflow. GitHub: QGIS plugin: GeoAgent: #EarthEngine #QGIS #OpenSource #GeoAI #Geospatial
1:11

An AI assistant for Google Earth Engine is now available in QGIS! You can explore and visualize any dataset from the 80+ PB Earth Engine Data Catalog using natural language, and run scalable geospatial analysis on demand without writing code. Every interaction automatically generates reusable code, making it easy to reproduce results, customize workflows, and transition from no-code to full scripting when needed. Upgrade the plugin to get started and bring AI-powered geospatial analytics directly into your QGIS workflow. GitHub: QGIS plugin: GeoAgent: #EarthEngine #QGIS #OpenSource #GeoAI #Geospatial

Qiusheng Wu

17,352 views • 2 months ago

Software development will never be the same. I want you to watch this video: This is a spec-driven development environment. 100% of your time goes to writing specs and managing agents. 0% goes to writing the code.
6:04

Software development will never be the same. I want you to watch this video: This is a spec-driven development environment. 100% of your time goes to writing specs and managing agents. 0% goes to writing the code.

Santiago

120,022 views • 6 months ago

Introducing FunctionGemma 🤏270m model for function calling 📱can run in your phone, browser or other devices 🤖designed to be specialized for your own tasks
0:50

Introducing FunctionGemma 🤏270m model for function calling 📱can run in your phone, browser or other devices 🤖designed to be specialized for your own tasks

Omar Sanseviero

301,773 views • 6 months ago

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more
0:30

train YOLOv9 on your dataset tutorial - run inference with a pre-trained COCO model - fine-tune model on custom dataset - evaluate the trained model - run inference with a fine-tuned model blogpost: ↓ read more

SkalskiP

111,874 views • 2 years ago

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!
0:22

Introducing the EASIEST way to fine-tune Qwen 2 VL with a Hugging Face dataset! (Link to repo in first reply). You can either fine-tune inside or a Gradio app or with a single line of Python. Simply select your favorite image-text dataset and fine-tune! A special thanks to Faen Zhang and all those at HuggingFace and those behind Qwen 2 VL. blog coming soon!

William J.B. Mattingly

21,466 views • 1 year ago

You can now Vibe Code MCP servers. Build, test, and publish MCP servers on GitHub without writing a single line of code. 1000+ servers live already.
0:21

You can now Vibe Code MCP servers. Build, test, and publish MCP servers on GitHub without writing a single line of code. 1000+ servers live already.

Unwind AI

27,228 views • 1 year ago

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:
0:28

Storing too many tools in your context window increases latency and can lead to wrong tool selection. In this demo, we used LFM2.5-ColBERT-350M as a filter to only select the five most relevant tools among 151 options. It's fast and reliable, even without any specific fine-tuning. Try the demo on Hugging Face! And learn more on our blog:

Liquid AI

33,089 views • 20 days ago