Aaron C Wacker PRO
AI & ML interests
Recent Activity
Organizations
awacke1's activity

Wow, I can't wait to try Reachy Mini and get back into telepresence development. Its been awhile but I had a web server I wrote years back that let you remote pilot a robot with a camera and video capture to cloud which was itself a peer web server / client.
It was capable of driving (tank treads) and picked and place with a little bull dozer/claw robot which was written with gcode for the motors. Once users figured out how to have it unplug itself it was short lived on the web.
Where can I buy one and get rocking with it?
Aaron

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.
🎥

This morning I completed the agentic demonstration with the SFT fine tuned model. Now the demo does the following:
- Allows user to download an open model they can specialize fine tune easily.
- Provide a CSV file with fine tune QA dataset.
- Using torch and transformers create an SFT output model with the new data trained to the model with 3 epochs.
- Ability to Test new model with list of QA questions and compare answers to expected.
- Demonstrate use of agents with smolagents tools.
Try it here:
https://huggingface.co/spaces/awacke1/TorchTransformers-NLP-CV-SFT
Download ML Models:
Build ML Models with Specialized Fine Tuning to a CSV:
Test your SFT Version with your changes.
Have an Agentic RAG Party with agents and your SFT model
Hope you enjoy and this demo is useful to you on your learning journey in ML!!
--Aaron Wacker
https://huggingface.co/awacke1
https://x.com/Aaron_Wacker

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


" 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.

This is a read-aloud lecture to answer questions of using language reasoning techniques in advanced AGI style chain of thought AI pipelines.
Produced using DeepResearchEvaluator located here: awacke1/DeepResearchEvaluator
Videos:
https://x.com/Aaron_Wacker/status/1874835790087463063
https://www.youtube.com/watch?v=fW_A1hH_7RM

After trying pretty much everything I gave the latest Grok2 a spin at converting my old malfunctioning Python/Gradio code which no longer adheres to syntax innovations and feature adds within python and gradio.
Grok2 in my opinion is the only one which could do this. Examine below instant one shot win by Grok2 with gradio! Greatest thing about it is it shows references via tweet so you can find where the intelligence was added so Grok2 is using modern syntax and unlike OpenAI and Anthropic, it produces innovative modern results aware of recent innovation.
Grok2 for the win I guess!
Tried a straw man example shown below which fails on others but works on Grok2:
Original which fails now if you upgrade Gradio:
import gradio as gr
from fastai.vision.all import *
import skimage
learn = load_learner('characters.pkl')
labels = learn.dls.vocab
def predict(img):
pred,pred_idx,probs = learn.predict(img)
return {labels[i]: float(probs[i]) for i in range(len(labels))}
title = "Video Game Character Classifier"
# description = "A pet breed classifier trained on the Oxford Pets dataset with fastai. Created as a demo for Gradio and HuggingFace Spaces."
#article="<p style='text-align: center'><a href='https://tmabraham.github.io/blog/gradio_hf_spaces_tutorial' target='_blank'>Blog post</a></p>"
examples = ['ellie.jpg','arthur.jpg','kratos.jpg','ellielou.jpg']
interpretation='default'
enable_queue=True
gr.Interface(fn=predict,inputs=gr.inputs.Image(shape=(128, 128)),outputs=gr.outputs.Label(),title=title,examples=examples,interpretation=interpretation,enable_queue=enable_queue).launch()
Second Grok2 prompt (first switched to blocks shown below).
Grok2's second shot with examples of errors gave working code and also tweet references!!
import gradio as gr
from fastai.vision.all import *
import skimage
learn = load_learner('characters.pkl')
labels = learn.dls.vocab
def predict(img):
pred, pred_idx, probs = learn.predict(img)
return {labels[i]: float(probs[i]) for i in range(len(labels))}
title = "Video Game Character Classifier"
examples = ['ellie.jpg', 'arthur.jpg', 'kratos.jpg', 'ellielou.jpg']
# Updated Gradio Interface with new syntax
with gr.Blocks() as demo:
gr.Markdown("# " + title)
# Use width and height instead of shape
image_input = gr.Image(width=128, height=128)
label_output = gr.Label()
# Create submit button
submit_btn = gr.Button("Classify")
submit_btn.click(fn=predict, inputs=image_input, outputs=label_output)
# Adding examples
gr.Examples(examples, inputs=image_input, outputs=label_output, fn=predict)
demo.launch()

🚲 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 & 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&ref_src=twsrc%5Etfw">#GPT</a> <a href="https://twitter.com/hashtag/Claude?src=hash&ref_src=twsrc%5Etfw">#Claude</a> <a href="https://twitter.com/hashtag/Huggingface?src=hash&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>— 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

Most excellent Dataset sir. This is quite useful. Thanks! Aaron

Link: ajibawa-2023/Software-Architecture
I am releasing a Large Dataset covering topics related to Software-Architecture. This dataset consists of around 450,000 lines of data in jsonl.
I have included following topics:
Architectural Frameworks
Architectural Patterns for Reliability
Architectural Patterns for Scalability
Architectural Patterns
Architectural Quality Attributes
Architectural Testing
Architectural Views
Architectural Decision-Making
Advanced Research
Cloud-Based Architectures
Component-Based Architecture
Data Architecture
Emerging Trends
Event-Driven Architecture
Evolvability and Maintainability
Microservices and Monolithic
Microservices Architecture
Security Architecture
Service-Oriented Architecture
Software Design Principles
and Many More!
This dataset is useful in LLM development. Also those who are working on developing Software development related LLMs then this dataset can be useful.
This dataset is very useful to Researchers as well.

open-llm-leaderboard/comparator
Dive into multi-model evaluations, pinpoint the best model for your needs, and explore insights across top open LLMs all in one place. Ready to level up your model comparison game?

Thankyou for the tips and insight on Gradio 5. Much appreciated,

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

Have you ever dreamt of an improbable books crossover, like Frodo from 𝘓𝘰𝘳𝘥 𝘰𝘧 𝘵𝘩𝘦 𝘙𝘪𝘯𝘨𝘴 becoming the main character of the 𝘖𝘥𝘺𝘴𝘴𝘦𝘺 or Emma Bovary from 𝘔𝘢𝘥𝘢𝘮𝘦 𝘉𝘰𝘷𝘢𝘳𝘺 acting as a modern-days Shakespearean Juliet?
Well, all of this is now possible! I'm thrilled to introduce my latest opensource product for storytelling: 𝐛𝐨𝐨𝐤𝐬-𝐦𝐢𝐱𝐞𝐫-𝐚𝐢 𝐯𝟎.𝟎.𝟎 !
Built with ReactJS and shipped directly to you on Spaces thanks to Docker, this webapp combines the power of two AI tools:
- gpt-4o-mini by OpenAI, which takes care of cooking new and intriguing plots starting from the user's instructions, the titles and the summaries of the two books to mix (summaries are scraped through Wikipedia)
- text2img realtime API by ModelsLab, which provides a stable diffusion pipeline to create a thumbnail for your newly-generated story
Everything is provided under a simple and intuitive UI, which uses chatscope's React template kit.
Curious of trying? The app is already live at:
as-cle-bert/books-mixer-ai
And you can also have a tour of the GitHub repo (and leave a little ⭐ while you're there):
https://github.com/AstraBert/books-mixer-ai
The documentation is still under construction, but will become available soon😊
Have fun!📚📚

Yes, they may be subpar and may require changes to llama.cpp to support the interleaved sliding window
Yes, I got excited when a conversion worked and released them ASAP
That said, generation seems to work right now and seems to mimic the output from spaces that are running the original model
I have appended -TEST to the model names in an attempt to indicate that they are not final or perfect, but if people still feel mislead and that it's not the right thing to do, please post (civilly) below your thoughts, I will highly consider pulling the conversions if that's what people think is best. After all, that's what I'm here for, in service to you all !

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!* 🚀

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 :

https://www.microsoft.com/en-us/research/
---
Aaron