AI & ML interests

AGI and ML Pipelines, Ambient IoT AI, Behavior Cognitive and Memory AI, Clinical Medical and Nursing AI, Genomics AI, GAN Gaming GAIL AR VR XR and Simulation AI, Graph Ontology KR KE AI, Languages and NLP AI, Quantum Compute GPU TPU NPU AI, Vision Image Document AI

Recent Activity

AIZeroToHero's activity

awacke1Β 
posted an update about 17 hours ago
view post
Post
450
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.
Sri-Vigneshwar-DJΒ 
posted an update 3 days ago
view post
Post
545
Checkout phi-4 from Microsoft, dropped a day ago... If you ❀️ the Phi series, then here is the GGUF - Sri-Vigneshwar-DJ/phi-4-GGUF. phi-4 is a 14B highly efficient open LLM that beats much larger models at math and reasoning - check out evaluations on the Open LLM.

Technical paper - https://arxiv.org/pdf/2412.08905 ; The Data Synthesis approach is interesting
Sri-Vigneshwar-DJΒ 
posted an update 6 days ago
view post
Post
2011
Just sharing a thought: I started using DeepSeek V3 a lot, and an idea struck me about agents "orchestrating during inference" on a test-time compute model like DeepSeek V3 or the O1 series.

Agents (Instruction + Function Calls + Memory) execute during inference, and based on the output decision, a decision is made to scale the time to reason or perform other tasks.
Sri-Vigneshwar-DJΒ 
posted an update 8 days ago
view post
Post
2314
Combining smolagents with Anthropic’s best practices simplifies building powerful AI agents:

1. Code-Based Agents: Write actions as Python code, reducing steps by 30%.
2. Prompt Chaining: Break tasks into sequential subtasks with validation gates.
3. Routing: Classify inputs and direct them to specialized handlers.
4. Fallback: Handle tasks even if classification fails.

https://huggingface.co/blog/Sri-Vigneshwar-DJ/building-effective-agents-with-anthropics-best-pra
awacke1Β 
posted an update 10 days ago
awacke1Β 
posted an update about 2 months ago
view post
Post
995
πŸ•ŠοΈHopeπŸ•ŠοΈ and βš–οΈJusticeβš–οΈ 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 πŸ•ŠοΈHopeπŸ•ŠοΈ and βš–οΈJusticeβš–οΈ 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
not-lainΒ 
posted an update about 2 months ago
view post
Post
2135
ever wondered how you can make an API call to a visual-question-answering model without sending an image url πŸ‘€

you can do that by converting your local image to base64 and sending it to the API.

recently I made some changes to my library "loadimg" that allows you to make converting images to base64 a breeze.
πŸ”— https://github.com/not-lain/loadimg

API request example πŸ› οΈ:
from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
awacke1Β 
posted an update 3 months ago
view post
Post
1951
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
Β·
awacke1Β 
posted an update 3 months ago
view post
Post
702
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

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

## 1. πŸ€” From 🦜 to 🧠: O1's Evolution

- **Thinking AI**: O1 ponders before replying; GPT models just predict. πŸ’‘

## 2. πŸ“š AI Memory: πŸ’Ύ + 🧩 = 🧠

- **Embeddings & Tokens**: Words ➑️ vectors, building knowledge. πŸ“–

## 3. πŸ” Swift Knowledge Retrieval

- **Vector Search & Indexing**: O1 finds info fast, citing reliable sources. πŸ”ŽπŸ“–

## 4. 🌳 Logic Trees with Mermaid Models

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

## 5. πŸ’» Coding Mastery

- **Multilingual & Current**: Speaks many code languages, always up-to-date. πŸ’»πŸ”„

## 6. πŸ† Breaking Records

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

## 7. πŸ’‘ Versatile Applications

- **Ultimate Assistant**: From fixing code to advancing research. πŸ› οΈπŸ”¬

## 8. 🏁 Racing Toward AGI

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

## 9. πŸ€– O1's Reasoning Pillars

- **🧠 Chain of Thought**: Step-by-step logic.
- **🎲 MCTS**: Simulates options, picks best path.
- **πŸ” Reflection**: Self-improves autonomously.
- **πŸ‹οΈβ€β™‚οΈ Reinforcement Learning**: Gets smarter over time.

---

*Stay curious, keep coding!* πŸš€
awacke1Β 
posted an update 3 months ago
view post
Post
581
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 :
https://huggingface.co/microsoft
https://www.microsoft.com/en-us/research/
---
Aaron
awacke1Β 
posted an update 3 months ago
view post
Post
997
Updated my πŸ“ΊRTVπŸ–ΌοΈ - Real Time Video AI app this morning.
URL: 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!
awacke1Β 
posted an update 4 months ago
awacke1Β 
posted an update 4 months ago
view post
Post
594
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
not-lainΒ 
posted an update 5 months ago
awacke1Β 
posted an update 6 months ago
view post
Post
1346
I just launched an exciting new multiplayer app powered by GPT-4o, enabling collaborative AI-driven queries in a single shared session!

### πŸ”— Try It Out! πŸ‘‰ Check out the GPT-4o Multiplayer App
Experience the future of collaborative AI by visiting our space on Hugging Face: awacke1/ChatStreamlitMultiplayer

πŸŽ‰ This innovative tool lets you and your team reason over:

###πŸ“ Text
###πŸ–ΌοΈ Image
###🎡 Audio
###πŸŽ₯ Video

## πŸ” Key Features

### Shared Contributions
Collaborate in real-time, seeing each other's inputs and contributions.
Enhances teamwork and fosters a collective approach to problem-solving.

### Diverse Media Integration
Seamlessly analyze and reason with text, images, audio, and video.
Breakthrough capabilities in handling complex media types, including air traffic control images and audio.

## πŸ› οΈ Real-World Testing
This morning, we tested the app using images and audio from air traffic controlβ€”a challenge that was nearly impossible to handle with ease just a few years ago. πŸšπŸ’¬

🌱 The Future of AI Collaboration
We believe AI Pair Programming is evolving into a new era of intelligence through shared contributions and teamwork. As we continue to develop, this app will enable groups to:

Generate detailed text responses πŸ“
Collaborate on code responses πŸ’»
Develop new AI programs together πŸ€–
not-lainΒ 
posted an update 6 months ago
view post
Post
7713
I am now a huggingface fellow πŸ₯³
Β·
awacke1Β 
posted an update 6 months ago
view post
Post
2748
βœ¨πŸš€ Claude Sonnet 3.5 API. It's already weaving digital magic!
πŸ§ πŸ’» Try it at my space: πŸ”— awacke1/AnthropicClaude3.5Sonnet-ACW

Kudos to @AnthropicAI for this elegant API! πŸ‘ #AI #CodeMagic #AnthropicAI Thanks Huggingface for hosting the best hub in the world for AI development!

Β·
not-lainΒ 
posted an update 7 months ago
view post
Post
2674
I have finished writing a blogpost about building an image-based retrieval system, This is one of the first-ever approaches to building such a pipeline using only open-source models/libraries πŸ€—

You can checkout the blogpost in https://huggingface.co/blog/not-lain/image-retriever and the associated space at not-lain/image-retriever .

✨ If you want to request another blog post consider letting me know down below or you can reach out to me through any of my social media

πŸ“– Happy reading !
not-lainΒ 
posted an update 7 months ago
view post
Post
1447
Hello beautiful people.
I wanted to thank everyone that read my blogpost and I am glad to share that we have achieved 11000 readers πŸ₯³
I couldn't have done this without you, so once again thanks a lot everyone for the support πŸ’–
If you haven't already you can read my blog post at: https://huggingface.co/blog/not-lain/rag-chatbot-using-llama3
not-lainΒ 
posted an update 7 months ago
view post
Post
2094
It is with great pleasure I inform you that huggingface's ModelHubMixin reached 200+ models on the hub πŸ₯³

ModelHubMixin is a class developed by HF to integrate AI models with the hub with ease and it comes with 3 methods :
* save_pretrained
* from_pretrained
* push_to_hub

Shoutout to @nielsr , @Wauplin and everyone else on HF for their awesome work πŸ€—

If you are not familiar with ModelHubMixin and you are looking for extra resources you might consider :
* docs: https://huggingface.co/docs/huggingface_hub/main/en/package_reference/mixins
πŸ”—blog about training models with the trainer API and using ModelHubMixin: https://huggingface.co/blog/not-lain/trainer-api-and-mixin-classes
πŸ”—GitHub repo with pip integration: https://github.com/not-lain/PyTorchModelHubMixin-template
πŸ”—basic guide: https://huggingface.co/posts/not-lain/884273241241808