ErwinH
@erwinlearns.bsky.social
Building the future of LLMs @ Google
Fine-tuning and LLMOps
My views
https://www.linkedin.com/in/erwinhuizenga/
Fine-tuning and LLMOps
My views
https://www.linkedin.com/in/erwinhuizenga/
DeepSeek has released their upgraded DeepSeek-R1-0528 model.
🔹 Improved benchmark performance
🔹Enhanced front-end capabilities
🔹Supports JSON output & function calling
We've made sure its available from day one on Vertex AI for deployment. with Nvidia's H200
🔹 Improved benchmark performance
🔹Enhanced front-end capabilities
🔹Supports JSON output & function calling
We've made sure its available from day one on Vertex AI for deployment. with Nvidia's H200
May 30, 2025 at 9:51 AM
DeepSeek has released their upgraded DeepSeek-R1-0528 model.
🔹 Improved benchmark performance
🔹Enhanced front-end capabilities
🔹Supports JSON output & function calling
We've made sure its available from day one on Vertex AI for deployment. with Nvidia's H200
🔹 Improved benchmark performance
🔹Enhanced front-end capabilities
🔹Supports JSON output & function calling
We've made sure its available from day one on Vertex AI for deployment. with Nvidia's H200
Are you running an AI startup? Google launched the AI Futures Fund.
Being part of this program will give startups early access to Google's latest AI models as well as resources, technical expertise and equity funding to accelerate their progress.
Apply here:
labs.google/aifuturesfund
Being part of this program will give startups early access to Google's latest AI models as well as resources, technical expertise and equity funding to accelerate their progress.
Apply here:
labs.google/aifuturesfund
May 26, 2025 at 3:19 AM
Are you running an AI startup? Google launched the AI Futures Fund.
Being part of this program will give startups early access to Google's latest AI models as well as resources, technical expertise and equity funding to accelerate their progress.
Apply here:
labs.google/aifuturesfund
Being part of this program will give startups early access to Google's latest AI models as well as resources, technical expertise and equity funding to accelerate their progress.
Apply here:
labs.google/aifuturesfund
Big A2A and ADK news from Google I/O. 📢
Today, we're announcing:
1️⃣An A2A Python SDK AND an updated A2A protocol spec (v0.2).
2️⃣A new Java SDK for Agent Development Kit (ADK) AND the v1.0.0 stable release of our Python ADK.
Read more in our launch blog 👇
developers.googleblog.com/en/agents-ad...
Today, we're announcing:
1️⃣An A2A Python SDK AND an updated A2A protocol spec (v0.2).
2️⃣A new Java SDK for Agent Development Kit (ADK) AND the v1.0.0 stable release of our Python ADK.
Read more in our launch blog 👇
developers.googleblog.com/en/agents-ad...
May 20, 2025 at 11:27 PM
Big A2A and ADK news from Google I/O. 📢
Today, we're announcing:
1️⃣An A2A Python SDK AND an updated A2A protocol spec (v0.2).
2️⃣A new Java SDK for Agent Development Kit (ADK) AND the v1.0.0 stable release of our Python ADK.
Read more in our launch blog 👇
developers.googleblog.com/en/agents-ad...
Today, we're announcing:
1️⃣An A2A Python SDK AND an updated A2A protocol spec (v0.2).
2️⃣A new Java SDK for Agent Development Kit (ADK) AND the v1.0.0 stable release of our Python ADK.
Read more in our launch blog 👇
developers.googleblog.com/en/agents-ad...
Don't miss the GoogleIO 2025 Keynotes! 🚀
I'm excited about our announcements. Watch the livestream to stay ahead of the curve.
Link below 👇
I'm excited about our announcements. Watch the livestream to stay ahead of the curve.
Link below 👇
May 20, 2025 at 3:27 AM
Don't miss the GoogleIO 2025 Keynotes! 🚀
I'm excited about our announcements. Watch the livestream to stay ahead of the curve.
Link below 👇
I'm excited about our announcements. Watch the livestream to stay ahead of the curve.
Link below 👇
Yesterday the DeepMind team introduced AlphaEvolve: a Gemini-powered coding agent for algorithm discovery.
What I find impressive is that a single system can contribute to numerous open problems in maths and computer science. Which proves that Agents can discover novel and useful algorithms
What I find impressive is that a single system can contribute to numerous open problems in maths and computer science. Which proves that Agents can discover novel and useful algorithms
May 16, 2025 at 1:40 AM
Yesterday the DeepMind team introduced AlphaEvolve: a Gemini-powered coding agent for algorithm discovery.
What I find impressive is that a single system can contribute to numerous open problems in maths and computer science. Which proves that Agents can discover novel and useful algorithms
What I find impressive is that a single system can contribute to numerous open problems in maths and computer science. Which proves that Agents can discover novel and useful algorithms
Google is running an Agents hackathon using the Agent Development Kit (ADK).
What it offers:
🛠️ Build with the Agent Development Kit (ADK)
🏆 $50K cash prize pool
🧑🏫 Insights from Google experts
Sign up link below 👇
What it offers:
🛠️ Build with the Agent Development Kit (ADK)
🏆 $50K cash prize pool
🧑🏫 Insights from Google experts
Sign up link below 👇
May 14, 2025 at 6:00 AM
Google is running an Agents hackathon using the Agent Development Kit (ADK).
What it offers:
🛠️ Build with the Agent Development Kit (ADK)
🏆 $50K cash prize pool
🧑🏫 Insights from Google experts
Sign up link below 👇
What it offers:
🛠️ Build with the Agent Development Kit (ADK)
🏆 $50K cash prize pool
🧑🏫 Insights from Google experts
Sign up link below 👇
Fine-tuning and deploying open models can be challenging.
Ivan Nardini and I documented how you can fine-tune and deploy Gemma 3 on Vertex AI.
Check it out and let us know your thoughts! 👇
www.youtube.com/watch?v=pC2D...
Ivan Nardini and I documented how you can fine-tune and deploy Gemma 3 on Vertex AI.
Check it out and let us know your thoughts! 👇
www.youtube.com/watch?v=pC2D...
Get started with Gemma 3 on Vertex AI
YouTube video by Google for Developers
www.youtube.com
May 13, 2025 at 2:48 AM
Fine-tuning and deploying open models can be challenging.
Ivan Nardini and I documented how you can fine-tune and deploy Gemma 3 on Vertex AI.
Check it out and let us know your thoughts! 👇
www.youtube.com/watch?v=pC2D...
Ivan Nardini and I documented how you can fine-tune and deploy Gemma 3 on Vertex AI.
Check it out and let us know your thoughts! 👇
www.youtube.com/watch?v=pC2D...
Insightful read on practical applications of Model Context Protocol (MCP) and the Agent Development Kit.
The post dives into common patterns developers can adopt. Great for anyone building with agents.
medium.com/google-cloud...
The post dives into common patterns developers can adopt. Great for anyone building with agents.
medium.com/google-cloud...
ADK meets MCP: Bridging Worlds of AI Agents
AI agent connects with the external tools via MCP server
medium.com
May 9, 2025 at 1:26 AM
Insightful read on practical applications of Model Context Protocol (MCP) and the Agent Development Kit.
The post dives into common patterns developers can adopt. Great for anyone building with agents.
medium.com/google-cloud...
The post dives into common patterns developers can adopt. Great for anyone building with agents.
medium.com/google-cloud...
Reposted by ErwinH
Happy 99th birthday to the man who gave voice to the wild. 🎉
Sir David Attenborough, thank you for a lifetime dedicated to the natural world, and for sharing its story with wisdom, wonder, and grace.
You've inspired generations to fall in love with nature.
Sir David Attenborough, thank you for a lifetime dedicated to the natural world, and for sharing its story with wisdom, wonder, and grace.
You've inspired generations to fall in love with nature.
May 8, 2025 at 7:09 AM
Happy 99th birthday to the man who gave voice to the wild. 🎉
Sir David Attenborough, thank you for a lifetime dedicated to the natural world, and for sharing its story with wisdom, wonder, and grace.
You've inspired generations to fall in love with nature.
Sir David Attenborough, thank you for a lifetime dedicated to the natural world, and for sharing its story with wisdom, wonder, and grace.
You've inspired generations to fall in love with nature.
We just dropped Gemini 2.0 Flash Image Generation. Its available on Vertex AI (preview) and AI Studio.
Offering better visual quality and more accurate text rendering.
Notebook below to get you started 👇
Offering better visual quality and more accurate text rendering.
Notebook below to get you started 👇
May 8, 2025 at 3:39 AM
We just dropped Gemini 2.0 Flash Image Generation. Its available on Vertex AI (preview) and AI Studio.
Offering better visual quality and more accurate text rendering.
Notebook below to get you started 👇
Offering better visual quality and more accurate text rendering.
Notebook below to get you started 👇
Gemini 2.5 Pro just got an upgrade.
It' got better at coding, with significant gains in front-end web development, editing, and transformation. We also fixed a bunch of function calling issue.
You can access it as gemini-2.5-pro-preview-05-06 on VertexAI and AIStudio
More details in 🧵
It' got better at coding, with significant gains in front-end web development, editing, and transformation. We also fixed a bunch of function calling issue.
You can access it as gemini-2.5-pro-preview-05-06 on VertexAI and AIStudio
More details in 🧵
May 7, 2025 at 4:06 AM
Gemini 2.5 Pro just got an upgrade.
It' got better at coding, with significant gains in front-end web development, editing, and transformation. We also fixed a bunch of function calling issue.
You can access it as gemini-2.5-pro-preview-05-06 on VertexAI and AIStudio
More details in 🧵
It' got better at coding, with significant gains in front-end web development, editing, and transformation. We also fixed a bunch of function calling issue.
You can access it as gemini-2.5-pro-preview-05-06 on VertexAI and AIStudio
More details in 🧵
This is cool. You can now use Gradio to build a MCP server in just a few lines of Python.
May 6, 2025 at 10:12 AM
This is cool. You can now use Gradio to build a MCP server in just a few lines of Python.
Google just published a 2nd 76-page whitepaper on AI Agents that covers more advanced topics:
> Agentic RAG
> Agent Evaluation
> Multi-Agent Evaluation
> Production Architectures
If you're comfortable with agent basics and looking to understand the next layer this is a great read 👇
> Agentic RAG
> Agent Evaluation
> Multi-Agent Evaluation
> Production Architectures
If you're comfortable with agent basics and looking to understand the next layer this is a great read 👇
May 6, 2025 at 3:31 AM
Google just published a 2nd 76-page whitepaper on AI Agents that covers more advanced topics:
> Agentic RAG
> Agent Evaluation
> Multi-Agent Evaluation
> Production Architectures
If you're comfortable with agent basics and looking to understand the next layer this is a great read 👇
> Agentic RAG
> Agent Evaluation
> Multi-Agent Evaluation
> Production Architectures
If you're comfortable with agent basics and looking to understand the next layer this is a great read 👇
Great tutorial by @kweinmeister.bsky.social 👇
Build a RAG for YOUR codebase in 5 easy steps! 🚀
Query w/ natural language using Gemini & Vertex AI RAG Engine, and chat in Vertex AI Studio.
🎬 Video: youtube.com/watch?v=sgKB...
📖 Article:
medium.com/google-cloud...
💾 Notebook:
github.com/kweinmeister...
Query w/ natural language using Gemini & Vertex AI RAG Engine, and chat in Vertex AI Studio.
🎬 Video: youtube.com/watch?v=sgKB...
📖 Article:
medium.com/google-cloud...
💾 Notebook:
github.com/kweinmeister...
RAG your Codebase with Vertex AI RAG Engine
Unlock the power of your codebase! 🚀 Learn how to use Google Cloud's Vertex AI RAG Engine to index an entire GitHub repository and ask complex questions abo...
youtube.com
May 6, 2025 at 2:56 AM
Great tutorial by @kweinmeister.bsky.social 👇
Interesting blog post by
@weightsbiases.bsky.social on the Agent2Agent (A2A) protocol.
The blog talks talks about how it works, its core components and how to use it with CrewAI and @langchain.bsky.social.
Blog below 👇
@weightsbiases.bsky.social on the Agent2Agent (A2A) protocol.
The blog talks talks about how it works, its core components and how to use it with CrewAI and @langchain.bsky.social.
Blog below 👇
May 5, 2025 at 1:22 AM
Interesting blog post by
@weightsbiases.bsky.social on the Agent2Agent (A2A) protocol.
The blog talks talks about how it works, its core components and how to use it with CrewAI and @langchain.bsky.social.
Blog below 👇
@weightsbiases.bsky.social on the Agent2Agent (A2A) protocol.
The blog talks talks about how it works, its core components and how to use it with CrewAI and @langchain.bsky.social.
Blog below 👇
Agent2Agent (A2A) updates:
💻 We've just added a demo showcasing agents using the A2A protocol to interact.
📄 We've refreshed the docs to lower the barrier for you to get started.
Keep sharing your A2A feedback!
💻 We've just added a demo showcasing agents using the A2A protocol to interact.
📄 We've refreshed the docs to lower the barrier for you to get started.
Keep sharing your A2A feedback!
May 2, 2025 at 3:01 AM
Agent2Agent (A2A) updates:
💻 We've just added a demo showcasing agents using the A2A protocol to interact.
📄 We've refreshed the docs to lower the barrier for you to get started.
Keep sharing your A2A feedback!
💻 We've just added a demo showcasing agents using the A2A protocol to interact.
📄 We've refreshed the docs to lower the barrier for you to get started.
Keep sharing your A2A feedback!
Gemma 3 fine-tuning just got a serious boost! 🚀 Axolotl v0.8.0 delivers:
- Up to 3.6x speedup vs HF+FA2
- ~50% memory reduction
- Now includes Sequence Parallelism, Cut-Cross Entropy & Liger kernels
Plus you can fine-tune Gemma-3 27B with just 21.6GB VRAM!
- Up to 3.6x speedup vs HF+FA2
- ~50% memory reduction
- Now includes Sequence Parallelism, Cut-Cross Entropy & Liger kernels
Plus you can fine-tune Gemma-3 27B with just 21.6GB VRAM!
April 30, 2025 at 4:51 AM
Gemma 3 fine-tuning just got a serious boost! 🚀 Axolotl v0.8.0 delivers:
- Up to 3.6x speedup vs HF+FA2
- ~50% memory reduction
- Now includes Sequence Parallelism, Cut-Cross Entropy & Liger kernels
Plus you can fine-tune Gemma-3 27B with just 21.6GB VRAM!
- Up to 3.6x speedup vs HF+FA2
- ~50% memory reduction
- Now includes Sequence Parallelism, Cut-Cross Entropy & Liger kernels
Plus you can fine-tune Gemma-3 27B with just 21.6GB VRAM!
Qwen 3 is out. Some highlights:
↔️Offers a wide range of sizes, from 0.6B to 235B.
🧠 Includes MoE variants.
🎛️ Hybrid Thinking Control with `enable_thinking=True`.
🌍 Multilingual Support: with support for 119 languages and dialects.
↔️Offers a wide range of sizes, from 0.6B to 235B.
🧠 Includes MoE variants.
🎛️ Hybrid Thinking Control with `enable_thinking=True`.
🌍 Multilingual Support: with support for 119 languages and dialects.
April 29, 2025 at 2:58 AM
Qwen 3 is out. Some highlights:
↔️Offers a wide range of sizes, from 0.6B to 235B.
🧠 Includes MoE variants.
🎛️ Hybrid Thinking Control with `enable_thinking=True`.
🌍 Multilingual Support: with support for 119 languages and dialects.
↔️Offers a wide range of sizes, from 0.6B to 235B.
🧠 Includes MoE variants.
🎛️ Hybrid Thinking Control with `enable_thinking=True`.
🌍 Multilingual Support: with support for 119 languages and dialects.
Interesting insights from
@FeinbergVlad
talk on Gemini pretraining.
This talk covers scaling laws and how scaling approaches might need to be modified in the face of inference constraints.
Link below 👇
@FeinbergVlad
talk on Gemini pretraining.
This talk covers scaling laws and how scaling approaches might need to be modified in the face of inference constraints.
Link below 👇
April 28, 2025 at 3:51 AM
Interesting insights from
@FeinbergVlad
talk on Gemini pretraining.
This talk covers scaling laws and how scaling approaches might need to be modified in the face of inference constraints.
Link below 👇
@FeinbergVlad
talk on Gemini pretraining.
This talk covers scaling laws and how scaling approaches might need to be modified in the face of inference constraints.
Link below 👇
We've just launched Gemini 2.5 Flash.
⚡️High quality for best cost
🧩 Ability to dynamically think on complex tasks
🎛️ Configurable thinking budget (decide how many tokens to allocate to "thinking".
⚡️High quality for best cost
🧩 Ability to dynamically think on complex tasks
🎛️ Configurable thinking budget (decide how many tokens to allocate to "thinking".
April 18, 2025 at 12:06 AM
We've just launched Gemini 2.5 Flash.
⚡️High quality for best cost
🧩 Ability to dynamically think on complex tasks
🎛️ Configurable thinking budget (decide how many tokens to allocate to "thinking".
⚡️High quality for best cost
🧩 Ability to dynamically think on complex tasks
🎛️ Configurable thinking budget (decide how many tokens to allocate to "thinking".
Setting up Gemma 3 with Ollama on Google Colab? I wrote down the steps I followed, including enabling streaming responses and handling multimodal inputs.
Details & steps on the blog ⤵️
Details & steps on the blog ⤵️
April 16, 2025 at 5:22 AM
Setting up Gemma 3 with Ollama on Google Colab? I wrote down the steps I followed, including enabling streaming responses and handling multimodal inputs.
Details & steps on the blog ⤵️
Details & steps on the blog ⤵️
Google Cloud Next 2025 and the ADK launch done ✅
On to the next.
On to the next.
April 12, 2025 at 1:02 AM
Google Cloud Next 2025 and the ADK launch done ✅
On to the next.
On to the next.
Yesterday Google released Agent Development Kit (ADK). Lots of you asked about the vision for ADK. To answer them clearly, we recorded a video explaining the thinking behind ADK and what problems we aim to solve for developers.
Watch here ⤵️
www.youtube.com/watch?v=zgrO...
Watch here ⤵️
www.youtube.com/watch?v=zgrO...
Introducing Agent Development Kit
YouTube video by Google for Developers
www.youtube.com
April 10, 2025 at 8:02 PM
Yesterday Google released Agent Development Kit (ADK). Lots of you asked about the vision for ADK. To answer them clearly, we recorded a video explaining the thinking behind ADK and what problems we aim to solve for developers.
Watch here ⤵️
www.youtube.com/watch?v=zgrO...
Watch here ⤵️
www.youtube.com/watch?v=zgrO...
Excited to share the Agent Development Kit (ADK)! 🚀 ADK is a new open-source, flexible framework designed to simplify the development and deployment of multi-agent systems.
Check out the quickstart below ⬇️
Check out the quickstart below ⬇️
April 9, 2025 at 2:41 PM
Excited to share the Agent Development Kit (ADK)! 🚀 ADK is a new open-source, flexible framework designed to simplify the development and deployment of multi-agent systems.
Check out the quickstart below ⬇️
Check out the quickstart below ⬇️
Get hands-on with Gemma 3 without the setup headache?
Hereby an updated guide that helps you get started with Gemma 3 and
@ollama
on Colab for a fast start. Based on one of our most popular 2024 posts. ⤵️
Hereby an updated guide that helps you get started with Gemma 3 and
@ollama
on Colab for a fast start. Based on one of our most popular 2024 posts. ⤵️
April 3, 2025 at 5:57 AM
Get hands-on with Gemma 3 without the setup headache?
Hereby an updated guide that helps you get started with Gemma 3 and
@ollama
on Colab for a fast start. Based on one of our most popular 2024 posts. ⤵️
Hereby an updated guide that helps you get started with Gemma 3 and
@ollama
on Colab for a fast start. Based on one of our most popular 2024 posts. ⤵️