Workshop June 13 Classroom

classroom

AI & ML interests

Deep Learning for computer vision

Classroom-workshop's activity

abidlabs 
posted an update 7 days ago
view post
Post
3587
HOW TO ADD MCP SUPPORT TO ANY 🤗 SPACE

Gradio now supports MCP! If you want to convert an existing Space, like this one hexgrad/Kokoro-TTS, so that you can use it with Claude Desktop / Cursor / Cline / TinyAgents / or any LLM that supports MCP, here's all you need to do:

1. Duplicate the Space (in the Settings Tab)
2. Upgrade the Gradio sdk_version to 5.28 (in the README.md)
3. Set mcp_server=True in launch()
4. (Optionally) add docstrings to the function so that the LLM knows how to use it, like this:

def generate(text, speed=1):
    """
    Convert text to speech audio.

    Parameters:
        text (str): The input text to be converted to speech.
        speed (float, optional): Playback speed of the generated speech.


That's it! Now your LLM will be able to talk to you 🤯
abidlabs 
posted an update 8 days ago
view post
Post
2441
Hi folks! Excited to share a new feature from the Gradio team along with a tutorial.

If you don't already know, Gradio is an open-source Python library used to build interfaces for machine learning models. Beyond just creating UIs, Gradio also exposes API capabilities and now, Gradio apps can be launched Model Context Protocol (MCP) servers for LLMs.

If you already know how to use Gradio, there are only two additional things you need to do:
* Add standard docstrings to your function (these will be used to generate the descriptions for your tools for the LLM)
* Set mcp_server=True in launch()


Here's a complete example (make sure you already have the latest version of Gradio installed):


import gradio as gr

def letter_counter(word, letter):
    """Count the occurrences of a specific letter in a word.
    
    Args:
        word: The word or phrase to analyze
        letter: The letter to count occurrences of
        
    Returns:
        The number of times the letter appears in the word
    """
    return word.lower().count(letter.lower())

demo = gr.Interface(
    fn=letter_counter,
    inputs=["text", "text"],
    outputs="number",
    title="Letter Counter",
    description="Count how many times a letter appears in a word"
)

demo.launch(mcp_server=True)



This is a very simple example, but you can add the ability to generate Ghibli images or speak emotions to any LLM that supports MCP. Once you have an MCP running locally, you can copy-paste the same app to host it on [Hugging Face Spaces](https://huggingface.co/spaces/) as well.

All free and open-source of course! Full tutorial: https://www.gradio.app/guides/building-mcp-server-with-gradio
  • 2 replies
·
julien-c 
posted an update 13 days ago
view post
Post
4015
BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript 🔥

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. 🤯

➡️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
  • 1 reply
·
abidlabs 
posted an update about 1 month ago
view post
Post
3781
JOURNEY TO 1 MILLION DEVELOPERS

5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface.

Today, Gradio is used by >1 million developers each month to build and share AI web apps. This includes some of the most popular open-source projects of all time, like Automatic1111, Fooocus, Oobabooga’s Text WebUI, Dall-E Mini, and LLaMA-Factory.

How did we get here? How did Gradio keep growing in the very crowded field of open-source Python libraries? I get this question a lot from folks who are building their own open-source libraries. This post distills some of the lessons that I have learned over the past few years:

1. Invest in good primitives, not high-level abstractions
2. Embed virality directly into your library
3. Focus on a (growing) niche
4. Your only roadmap should be rapid iteration
5. Maximize ways users can consume your library's outputs

1. Invest in good primitives, not high-level abstractions

When we first launched Gradio, we offered only one high-level class (gr.Interface), which created a complete web app from a single Python function. We quickly realized that developers wanted to create other kinds of apps (e.g. multi-step workflows, chatbots, streaming applications), but as we started listing out the apps users wanted to build, we realized what we needed to do:

Read the rest here: https://x.com/abidlabs/status/1907886
awacke1 
posted an update about 1 month ago
view post
Post
1621
AI Vision & SFT Titans 🌟 Turns PDFs into text, snaps pics, and births AI art.

https://huggingface.co/spaces/awacke1/TorchTransformers-Diffusion-CV-SFT

1. OCR a grocery list or train a titan while sipping coffee? ☕
2. Camera Snap 📷: Capture life’s chaos—your cat’s face or that weird receipt. Proof you’re a spy!
3. OCR 🔍: PDFs beg for mercy as GPT-4o extracts text.
4. Image Gen 🎨: Prompt “neon superhero me”
5. PDF 📄: Double-page OCR Single-page sniping

Build Titans 🌱: Train tiny AI models. 💪Characters🧑‍🎨: Craft quirky heroes.
🎥

julien-c 
posted an update about 2 months ago
view post
Post
3744
Important notice 🚨

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference – with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.
·
awacke1 
posted an update about 2 months ago
view post
Post
2300
I introduce MIT license

ML Model Specialize Fine Tuner app "SFT Tiny Titans" 🚀

Demo video with source.

Download, train, SFT, and test your models, easy as 1-2-3!
URL: awacke1/TorchTransformers-NLP-CV-SFT
  • 2 replies
·
awacke1 
posted an update 2 months ago
view post
Post
2484
🚀 Blast into the future with ZaxxonGalaxian – a thrilling 3D action game where you navigate epic battles through towering 3D cityscapes! Face off against relentless swarm bots, climb the leaderboard, and dominate the skies. awacke1/ZaxxoGalaxian
awacke1 
posted an update 4 months ago
view post
Post
3206
Deep Research Evaluator was asked:
" design a coral defense mechanism that upon sensing say an acid that's causing coral reefs to have a carbon dioxide issue it develops... please create a plan and a design for this\n
"
It picks these three as best combined solution.

1. [Reef-insight: A framework for reef habitat mapping with clustering methods via remote sensing]...
2. Phone a friend: [Learning to Communicate and Collaborate in a Competitive Multi-Agent Setup to Clean the Ocean from Macroplastics]...
3. World Solve: [Dependence of Physiochemical Features on Marine Chlorophyll Analysis with Learning Techniques]


To design a system that allows coralows coral reefs to respond to increased acidity levels in their environment, we can create a network of pH sensors and dispersal units that can detect changes in pH levels and release a base solution to neutralize the acid.

1. pH Sensors: The first component of the system would be a network of pH sensors placed strategically throughout the coral reef. These sensors would be small, durable, and able to withstand the harsh conditions of the ocean. They would be placed at various depths and locations within the reef to ensure accurate and comprehensive monitoring of pH levels.
2. Base Dispersal Units: Once the pH sensors detect a decrease in pH levels, they would trigger the base dispersal units to release a base solution into the water. These units would be strategically placed around the reef and would be able to release a controlled amount of base solution to neutralize the acidity in the water.
3. Water Dispersal Mechanism: The base dispersal units would be connected to a water dispersal mechanism that would allow the base solution to be distributed evenly around the reef. This could be achieved through a series of pipes or channels that would distribute the base solution in a controlled and targeted manner.
awacke1 
posted an update 4 months ago
julien-c 
posted an update 5 months ago
view post
Post
10687
After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team
·
julien-c 
posted an update 5 months ago
view post
Post
3222
wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct
awacke1 
posted an update 6 months ago
view post
Post
1022
🕊️Hope🕊️ and ⚖️Justice⚖️ AI
🚲 Stolen bike in Denver FOUND - Sometimes hope & justice DO prevail.

🎬 So I Created an AI+Art+Music tribute:
-🧠 AI App that Evaluates GPT-4o vs Claude:
awacke1/RescuerOfStolenBikes
https://x.com/Aaron_Wacker/status/1857640877986033980?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1857640877986033980%7Ctwgr%5E203a5022b0eb4c41ee8c1dd9f158330216ac5be1%7Ctwcon%5Es1_c10&ref_url=https%3A%2F%2Fpublish.twitter.com%2F%3Furl%3Dhttps%3A%2F%2Ftwitter.com%2FAaron_Wacker%2Fstatus%2F1857640877986033980

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">QT your 🕊️Hope🕊️ and ⚖️Justice⚖️ art🎨<br><br>🚲 Stolen bike in Denver FOUND! <br> - Sometimes hope &amp; justice DO prevail! <br><br>🎬 Created an AI+Art+Music tribute: <br> -🧠 AI App that Evaluates GPT-4o vs Claude: <a href="https://t.co/odrYdaeizZ">https://t.co/odrYdaeizZ</a><br> <a href="https://twitter.com/hashtag/GPT?src=hash&amp;ref_src=twsrc%5Etfw">#GPT</a> <a href="https://twitter.com/hashtag/Claude?src=hash&amp;ref_src=twsrc%5Etfw">#Claude</a> <a href="https://twitter.com/hashtag/Huggingface?src=hash&amp;ref_src=twsrc%5Etfw">#Huggingface</a> <a href="https://twitter.com/OpenAI?ref_src=twsrc%5Etfw">@OpenAI</a> <a href="https://twitter.com/AnthropicAI?ref_src=twsrc%5Etfw">@AnthropicAI</a> <a href="https://t.co/Q9wGNzLm5C">pic.twitter.com/Q9wGNzLm5C</a></p>&mdash; Aaron Wacker (@Aaron_Wacker) <a href="https://twitter.com/Aaron_Wacker/status/1857640877986033980?ref_src=twsrc%5Etfw">November 16, 2024</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>


#GPT #Claude #Huggingface
@OpenAI
@AnthropicAI
awacke1 
posted an update 7 months ago
view post
Post
1974
Since 2022 I have been trying to understand how to support advancement of the two best python patterns for AI development which are:
1. Streamlit
2. Gradio

The reason I chose them in this order was the fact that the streamlit library had the timing drop on gradio by being available with near perfection about a year or two before training data tap of GPT.

Nowadays its important that if you want current code to be right on generation it requires understanding of consistency in code method names so no manual intervention is required with each try.

With GPT and Claude being my top two for best AI pair programming models, I gravitate towards streamlit since aside from common repeat errors on cache and experimental functions circa 2022 were not solidified.
Its consistency therefore lacks human correction needs. Old dataset error situations are minimal.

Now, I seek to make it consistent on gradio side. Why? Gradio lapped streamlit for blocks paradigm and API for free which are I feel are amazing features which change software engineering forever.

For a few months I thought BigCode would become the new best model due to its training corpus datasets, yet I never felt it got to market as the next best AI coder model.

I am curious on Gradio's future and how. If the two main models (GPT and Claude) pick up the last few years, I could then code with AI without manual intervention. As it stands today Gradio is better if you could get the best coding models to not repeatedly confuse old syntax as current syntax yet we do live in an imperfect world!

Is anyone using an AI pair programming model that rocks with Gradio's latest syntax? I would like to code with a model that knows how to not miss the advancements and syntax changes that gradio has had in the past few years. Trying grok2 as well.

My IDE coding love is HF. Its hands down faster (100x) than other cloud paradigms. Any tips on models best for gradio coding I can use?

--Aaron
·
awacke1 
posted an update 7 months ago
view post
Post
717
Today I was able to solve a very difficult coding session with GPT-4o which ended up solving integrations on a very large scale. So I decided to look a bit more into how its reasoners work. Below is a fun markdown emoji outline about what I learned today and what I'm pursuing.

Hope you enjoy! Cheers, Aaron.

Also here are my favorite last 4 spaces I am working on:
1. GPT4O: awacke1/GPT-4o-omni-text-audio-image-video
2. Claude:
awacke1/AnthropicClaude3.5Sonnet-ACW
3. MSGraph M365: awacke1/MSGraphAPI
4. Azure Cosmos DB: Now with Research AI! awacke1/AzureCosmosDBUI

# 🚀 OpenAI's O1 Models: A Quantum Leap in AI

## 1. 🤔 From 🦜 to 🧠: O1's Evolution

- **Thinking AI**: O1 ponders before replying; GPT models just predict. 💡

## 2. 📚 AI Memory: 💾 + 🧩 = 🧠

- **Embeddings & Tokens**: Words ➡️ vectors, building knowledge. 📖

## 3. 🔍 Swift Knowledge Retrieval

- **Vector Search & Indexing**: O1 finds info fast, citing reliable sources. 🔎📖

## 4. 🌳 Logic Trees with Mermaid Models

- **Flowchart Reasoning**: O1 structures thoughts like diagrams. 🎨🌐

## 5. 💻 Coding Mastery

- **Multilingual & Current**: Speaks many code languages, always up-to-date. 💻🔄

## 6. 🏆 Breaking Records

- **92.3% MMLU Score**: O1 outperforms humans, setting new AI standards. 🏅

## 7. 💡 Versatile Applications

- **Ultimate Assistant**: From fixing code to advancing research. 🛠️🔬

## 8. 🏁 Racing Toward AGI

- **OpenAI Leads**: O1 brings us closer to true AI intelligence. 🚀

## 9. 🤖 O1's Reasoning Pillars

- **🧠 Chain of Thought**: Step-by-step logic.
- **🎲 MCTS**: Simulates options, picks best path.
- **🔍 Reflection**: Self-improves autonomously.
- **🏋️‍♂️ Reinforcement Learning**: Gets smarter over time.

---

*Stay curious, keep coding!* 🚀
awacke1 
posted an update 7 months ago
view post
Post
595
I have finally completed a working full Azure and Microsoft MS Graph API implementation which can use all the interesting MS AI features in M365 products to manage CRUD patterns for the graph features across products.

This app shows initial implementation of security, authentication, scopes, and access to Outlook, Calendar, Tasks, Onedrive and other apps for CRUD pattern as AI agent service skills to integrate with your AI workflow.


Below are initial screens showing integration:

URL: awacke1/MSGraphAPI
Discussion: awacke1/MSGraphAPI#5

Best of AI on @Azure and @Microsoft on @HuggingFace :
microsoft
https://www.microsoft.com/en-us/research/
---
Aaron
awacke1 
posted an update 7 months ago
view post
Post
1016
Updated my 📺RTV🖼️ - Real Time Video AI app this morning.
URL: https://huggingface.co/spaces/awacke1/stable-video-diffusion

It uses Stable Diffusion to dynamically create videos from images in input directory or uploaded using A10 GPU on Huggingface.


Samples below.

I may transition this to Zero GPU if I can. During Christmas when I revised this I had my highest billing from HF yet due to GPU usage. It is still the best turn key GPU out and Image2Video is a killer app. Thanks HF for the possibilities!
abidlabs 
posted an update 7 months ago
view post
Post
6264
👋 Hi Gradio community,

I'm excited to share that Gradio 5 will launch in October with improvements across security, performance, SEO, design (see the screenshot for Gradio 4 vs. Gradio 5), and user experience, making Gradio a mature framework for web-based ML applications.

Gradio 5 is currently in beta, so if you'd like to try it out early, please refer to the instructions below:

---------- Installation -------------

Gradio 5 depends on Python 3.10 or higher, so if you are running Gradio locally, please ensure that you have Python 3.10 or higher, or download it here: https://www.python.org/downloads/

* Locally: If you are running gradio locally, simply install the release candidate with pip install gradio --pre
* Spaces: If you would like to update an existing gradio Space to use Gradio 5, you can simply update the sdk_version to be 5.0.0b3 in the README.md file on Spaces.

In most cases, that’s all you have to do to run Gradio 5.0. If you start your Gradio application, you should see your Gradio app running, with a fresh new UI.

-----------------------------

Fore more information, please see: https://github.com/gradio-app/gradio/issues/9463
  • 2 replies
·
awacke1 
posted an update 7 months ago
awacke1 
posted an update 8 months ago
view post
Post
606
I am integrating Azure Cosmos DB, the database system that backs GPT conversations into my workflow, and experimenting with new patterns to accelerate dataset evolution for evaluation and training of AI.

While initially using it for research prompts and research outputs using my GPT-4o client here which can interface and search ArXiv, I am excited to try out some new features specifically for AI at scale. Research on memory augmentation is shown. awacke1/GPT-4o-omni-text-audio-image-video

awacke1/AzureCosmosDBUI