# Google Colab Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/google-colab
> Markdown URL: https://aitinkerers.org/technologies/google-colab.md
> Technology record last updated: 2026-09-18T15:13:53Z
> Generated: 2026-09-20T15:43:47Z

Google Colab is a free, hosted Jupyter Notebook service providing no-setup access to cloud computing resources, including NVIDIA GPUs and Google TPUs, for Python development.

Google Colaboratory (Colab) delivers a zero-configuration, cloud-based Jupyter Notebook environment, eliminating local setup for Python coding. This platform is specifically optimized for data science, machine learning, and education, integrating seamlessly with Google Drive for document storage and sharing (like Google Docs). Crucially, Colab provides limited, free access to high-end compute resources (GPUs and TPUs), which significantly accelerates intensive tasks like training large neural networks with frameworks such as TensorFlow and PyTorch. Users can write, execute, and share interactive code and rich text documents instantly, making it a powerful tool for rapid prototyping and collaborative research.

- Official technology site: https://colab.research.google.com/
- Public AI Tinkerers demos and talks: 12
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Training/Generating Absurd Cat Standup Videos](https://la.aitinkerers.org/talks/rsvp_7-heCmu8l0U)

I will be using Python/LLAMA-3 model to train a Seinfeld Style Monologue Generating LLM model and use Veo 3 to automatically make Absurd Cat Standup Videos. -I first scraped all Seinfeld scripts from https://www.seinfeldscripts.com/ -I captured/cleaned/formatted monologue data from the scraped Seinfeld scripts. -I used Python/Ollama to train the Llama 3 8b model to make an LLM that can generate seinfeld style monologue by subject. -I used the output of the trained LLM to make cat standup videos through Veo 3.

- Event context: Aug 16 - AI Tinkerers LA: Beauty, Bytes, and Venice Beach Vibes 🌊✨🤖 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_7-heCmu8l0U

### [The Geometry of Identity: High-Performance Matching with LightGlue](https://hong-kong.aitinkerers.org/talks/rsvp_CKcqvusIVsI)

In this deep dive, we move beyond the "black box" of face detection to dissect the underlying logic of neural feature matching. While traditional biometric systems often rely on global embeddings, this session explores the mechanics of sparse feature matching and how it can be used to quantify similarity with sub-millisecond precision. We will focus on the end-to-end pipeline: starting with classical keypoint extraction using SIFT, followed by state-of-the-art neural matching via LightGlue. We will explore how LightGlue’s transformer-based architecture utilises attention mechanisms to adaptively match SIFT keypoints. Furthermore, we will discuss how these complex models are optimised for real-time edge inference—a critical requirement for modern robotics and spatial computing. I will showcase two real-world implementation examples, including an interactive Google Colab notebook, so please bring your laptops.

- Event context: AI Tinkerers Hong Kong: Deep Dive Series - Deep Dive featuring Spatial Computing and Robotics — 2026-02-05 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_CKcqvusIVsI

### [Beyond Text: Hacking Transformers to Detect Anomalies in Million-Scale Netflow Data](https://toronto.aitinkerers.org/talks/rsvp_UxSNvJhCwH4)

Everyone uses Transformers for chat, but I wanted to see if they could catch hackers. In this demo, I’ll show how I forced NLP models (like ELECTRA) to 'read' & classify network traffic by treating diverse IoT datasets as text, graph-embedding, and even quantum-encoding. I’ll skip the slides and scroll through my Colab notebooks to show the messy reality of this experiment. You’ll see the custom data transformation scripts I wrote to tokenize IP addresses and build traffic graphs, the model definitions where I adapted the Transformer architectures, and the final code module that fuses these four wild modalities together to outperform standard detection methods.

- Event context: AI Tinkerers Toronto - January 2026 Meetup at Google! — 2026-01-29 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_UxSNvJhCwH4

### [Multimodal SLMs: Qwen 2.5 and Air-Gapped Document Intelligence for Confidential Data](https://hong-kong.aitinkerers.org/talks/rsvp_wdu0jEPpJYA)

I'm helping Branches of Hope (a charity in Hong Kong dedicated to assisting refugees) effectively digitise their confidential refugee records into structured data. As a result, I've built a solution that can be air-gapped, on-prem utilising the open-source Qwen2.5-VL-7B model. Through this, I found that even SLMs are far more effective at OCR than traditional deep-learning based approaches (e.g. Tesseract). In fact they are so good that the guidance you provide in the prompt is vital. I've now updated to using the latest Qwen3-VL-8B-Instruct model, and I will also highlight the changes in power that the latest open-source models provide.

- Event context: AI Tinkerers Hong Kong Meetup - November 27th — 2025-11-27 — Hong Kong
- Public talk page: https://hong-kong.aitinkerers.org/talks/rsvp_wdu0jEPpJYA

### [Red-Team AI models before Your Users Do](https://atlanta.aitinkerers.org/talks/rsvp_WNRew-MWc8w)

Users will always find bold and innovative ways to use your product. Some of these ways could cause harm. As developers and product managers, we're responsible for ensuring that the products we make are safe. To make safe products, we need to test them. We want to present testing frameworks that the audience can use to make safer AI products.

- Event context: 1 Year Anniversary Meetup — 2025-07-31 — Atlanta
- Public talk page: https://atlanta.aitinkerers.org/talks/rsvp_WNRew-MWc8w

### [AI Agents vs Agentic AI](https://austin.aitinkerers.org/talks/rsvp_TOjcdkVRYNg)

An example walkthrough on what is AI agent and what an Agentic AI is, their difference and use cases.

- Event context: Community AI Demos – Austin • July 10 2025 — 2025-07-10 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_TOjcdkVRYNg

### [SlateFront AI: A new way to learn with AI, visually.](https://abu-dhabi.aitinkerers.org/talks/rsvp_GkYfScCkcU0)

SlateFront is an AI-powered tool that generates mathematical animations and full explainer videos for math and physics concepts instantly, from just text or drawings.

- Event context: AI Tinkerers - Abu Dhabi Meetup #4 (May 2025) — 2025-05-22 — Abu Dhabi
- Public talk page: https://abu-dhabi.aitinkerers.org/talks/rsvp_GkYfScCkcU0

### [Modelo de clasificación de imágenes basado en Transformers para la evaluación de daños estructurales post-sísmicos de acuerdo con la Escala Macrosísmica europea: comparativa con técnicas de aprendizaje de máquina](https://quito.aitinkerers.org/talks/rsvp_IxDDfiiTmsU)

Fue mi tema de tesis consistió en comparar arquitecturas tradicionales de redes neuronales convolucionales (CNN) con modelos basados en Transformers, específicamente DeiT (Data-efficient Image Transformers), para la clasificación automática de imágenes de estructuras afectadas por sismos. Se trabajó con un dataset de 1500 imágenes (750 de mampostería y 750 de hormigón armado), evaluando el daño estructural conforme a la Escala Macrosísmica Europea (EMS-98). Se aplicaron técnicas de data aumentaron. La comparación se hizo con una tesis previa que usaba modelos CNN como VGG16, DenseNet121, MobileNetV2, entre otros, para contrastarlos con el desempeño de DeiT.

- Event context: AI Tinkerers - Quito Primer Meetup (Abril) — 2025-04-24 — Quito
- Public talk page: https://quito.aitinkerers.org/talks/rsvp_IxDDfiiTmsU

### [Automating Colab-to-API Deployment](https://boston.aitinkerers.org/talks/rsvp_wzvMa8vbzHs)

I'll demo a pipeline I'm working on to convert Colab notebooks into production-ready APIs.

- Event context: AI Tinkerers Boston November Meetup — 2024-11-25 — Boston
- Public talk page: https://boston.aitinkerers.org/talks/rsvp_wzvMa8vbzHs

### [Exploring Singapore's Open Data to find Market Trends Using LLMs: Insights from Data.Gov.SG and a Case Study of Pandemic Impacts](https://singapore.aitinkerers.org/talks/rsvp__2Zu-1FEZzU)

Analyze the Job Vacancy dataset to explore job market changes from 2020 to 2024 using LLMs, Python and Colab. learn how you can use Colab to tinker with various LLM models and gen ai services like Google Gemini and other LLMs from huggingface. Key Takeaways: Pandemic Impact: The Covid-19 pandemic significantly affected job markets, with notable spikes in Community and Social Services and varied impacts across other sectors. Data Insights: Combining job data with Covid trends highlights how different industries were influenced. I used Python and Colab for this analysis and shared my findings in a Colab notebook. Dive in, explore, and see what insights you can uncover! Let’s discuss how open data can drive valuable insights.

- Event context: AI Tinkerers Singapore: Inaugural Meetup - August 2nd, 2024 — 2024-08-02 — Singapore
- Public talk page: https://singapore.aitinkerers.org/talks/rsvp__2Zu-1FEZzU

### [LLaVA Next Interleave](https://austin.aitinkerers.org/talks/rsvp_VK2vrPH1aUI)

LLaVA Next Interleave is an exciting new model by llms labs that takes any number of videos & images, and in one inference call, compare/chat about/describe them i want to talk about the non obvious, interesting parts of the model's use cases, running the model yourself/deployment & integration/hacks for use in apps. And answer any questions.

- Event context: July Meetup: Community AI Demos — 2024-07-11 — Austin
- Public talk page: https://austin.aitinkerers.org/talks/rsvp_VK2vrPH1aUI

### [Full Mamba (SSM) with Agent Attention and Fast Feed Forward Sparse Activations](https://la.aitinkerers.org/talks/rsvp_-gf4Q3eqX1I)

Implemented some code I'd like to share with a live demonstration on training I started with some boilerplate code https://colab.research.google.com/drive/1g9qpeVcFa0ca0cnhmqusO4RZtQdh9umY compared with straight mamba as from hf models https://huggingface.co/state-spaces/mamba-x After trying both, realized the former trained better due to the added attention layer. Using the custom code. I was able to implement the following papers Exponentially Faster Language Modelling https://arxiv.org/abs/2311.10770 Agent Attention: On the Integration of Softmax and Linear Attention https://arxiv.org/abs/2312.08874 For small use cases it shows promise in less than 24 hours (for example, training on quotes). Going to be a live demo. Can be done all in one file less than 600 lines.

- Event context: Jan 10 - AI Tinkerers Meetup - FOR BUILDERS — 2024-01-11 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_-gf4Q3eqX1I

## Related Technologies

- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [Gemini](https://aitinkerers.org/technologies/gemini) ([Markdown](https://aitinkerers.org/technologies/gemini.md)) — 188 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos
- [Transformers](https://aitinkerers.org/technologies/transformers) ([Markdown](https://aitinkerers.org/technologies/transformers.md)) — 148 public demos
- [Agent Attention](https://aitinkerers.org/technologies/agent-attention) ([Markdown](https://aitinkerers.org/technologies/agent-attention.md)) — 1 public demo
- [API](https://aitinkerers.org/technologies/api) ([Markdown](https://aitinkerers.org/technologies/api.md)) — 19 public demos
- [Apple App Store](https://aitinkerers.org/technologies/apple-app-store) ([Markdown](https://aitinkerers.org/technologies/apple-app-store.md)) — 1 public demo
- [AWS](https://aitinkerers.org/technologies/aws) ([Markdown](https://aitinkerers.org/technologies/aws.md)) — 38 public demos
- [Chat](https://aitinkerers.org/technologies/chat) ([Markdown](https://aitinkerers.org/technologies/chat.md)) — 4 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Chat Uncensored AI](https://aitinkerers.org/technologies/chat-uncensored-ai) ([Markdown](https://aitinkerers.org/technologies/chat-uncensored-ai.md)) — 1 public demo
- [Claude-3](https://aitinkerers.org/technologies/claude-3) ([Markdown](https://aitinkerers.org/technologies/claude-3.md)) — 110 public demos
- [Data](https://aitinkerers.org/technologies/data) ([Markdown](https://aitinkerers.org/technologies/data.md)) — 8 public demos
- [DeiT](https://aitinkerers.org/technologies/deit) ([Markdown](https://aitinkerers.org/technologies/deit.md)) — 1 public demo
- [DenseNet121](https://aitinkerers.org/technologies/densenet121) ([Markdown](https://aitinkerers.org/technologies/densenet121.md)) — 1 public demo
- [Django](https://aitinkerers.org/technologies/django) ([Markdown](https://aitinkerers.org/technologies/django.md)) — 15 public demos
- [Docker](https://aitinkerers.org/technologies/docker) ([Markdown](https://aitinkerers.org/technologies/docker.md)) — 147 public demos