AI & ML interests

Training DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)

Recent Activity

training-transformers-together's activity

awacke1Β 
posted an update about 5 hours ago
view post
Post
120
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.
awacke1Β 
posted an update 9 days ago
lhoestqΒ 
posted an update about 1 month ago
view post
Post
1697
Made a HF Dataset editor a la gg sheets here: lhoestq/dataset-spreadsheets

With Dataset Spreadsheets:
✏️ Edit datasets in the UI
πŸ”— Share link with collaborators
🐍 Use locally in DuckDB or Python

Available for the 100,000+ parquet datasets on HF :)
thomwolfΒ 
posted an update about 1 month ago
view post
Post
4714
We are proud to announce HuggingFaceFW/fineweb-2: A sparkling update to HuggingFaceFW/fineweb with 1000s of πŸ—£οΈlanguages.

We applied the same data-driven approach that led to SOTA English performance in🍷 FineWeb to thousands of languages.

πŸ₯‚ FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.

The dataset is released under the permissive πŸ“œ ODC-By 1.0 license, and the πŸ’» code to reproduce it and our evaluations is public.

We will very soon announce a big community project, and are working on a πŸ“ blogpost walking you through the entire dataset creation process. Stay tuned!

In the mean time come ask us question on our chat place: HuggingFaceFW/discussion

H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
  • 2 replies
Β·
thomwolfΒ 
posted an update about 1 month ago
thomwolfΒ 
posted an update about 1 month ago
thomwolfΒ 
posted an update about 2 months ago
thomwolfΒ 
posted an update about 2 months 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
thomwolfΒ 
posted an update 3 months ago
view post
Post
4154
Parents in the 1990: Teach the kids to code
Parents now: Teach the kids to fix the code when it starts walking around πŸ€–βœ¨
  • 2 replies
Β·
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
blanchonΒ 
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