John Smith's picture

John Smith PRO

John6666

AI & ML interests

None yet

Recent Activity

liked a model 24 minutes ago
oriental-lab/Tr-Jp-LLM-1.5B-v2
liked a model 24 minutes ago
mradermacher/Tr-Jp-LLM-1.5B-v2-GGUF
liked a model 32 minutes ago
oriental-lab/Tr-Jp-LLM-1.5B
View all activity

Organizations

open/ acc's profile picture Solving Real World Problems's profile picture FashionStash Group meeting's profile picture No More Copyright's profile picture

John6666's activity

replied to dal4933's post about 2 hours ago
reacted to etemiz's post with 👀 about 3 hours ago
reacted to chansung's post with ❤️ about 3 hours ago
view post
Post
1107
simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL

I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!
·
reacted to freddyaboulton's post with 👀 about 3 hours ago
view post
Post
510
Ever wanted to share your AI creations with friends? ✨

Screenshots are fine, but imagine letting others play with your ACTUAL model!

Introducing Gradio deep links 🔗 - now you can share interactive AI apps, not just images.

Add a gr.DeepLinkButton to any app and get shareable URLs that let ANYONE experiment with your models.

reacted to philschmid's post with 🔥 about 3 hours ago
view post
Post
510
Gemini 2.5 Pro, thinking by default! We excited launch our best Gemini model for reasoning, multimodal and coding yet! #1 on LMSYS, Humanity’s Last Exam, AIME and GPQA and more!

TL;DR:
- 💻 Best Gemini coding model yet, particularly for web development (excels on LiveCodeBench).
- 🧠 Default "Thinking" with up to 64k token output
- 🌌 1 Million multimodal input context for text, image, video, audio, and pdf
- 🛠️ Function calling, structured output, google search & code execution.
- 🏆  #1 on LMArena & sota on AIME, GPQA, Humanity's Last Exam
- 💡 Knowledge cut of January 2025
- 🤗 Available for free as Experimental in AI Studio, Gemini API & Gemini APP
- 🚀 Rate limits - Free 2 RPM 50 req/day

Try it ⬇️

https://aistudio.google.com/?model=gemini-2.5-pro-exp-03-25
reacted to smirki's post with 👀 about 3 hours ago
view post
Post
293
I was able to make a demo dashboard application with my react model through prompting. You can play with it here: Tesslate/Tessa-T1-14B

http://playcode.io/2309196

What my react model made (prompted each file individually)
Ex.
Create a React component named Header that accepts the following props:

logo (string): the URL to the logo image

title (string): the title text to display

menuItems (array of objects): each object should contain a label (string) and href (string)
The Header should render a logo (an <img>), the title (e.g., in an <h1>), and a navigation menu with links. The component should be responsive with a mobile menu option. Export it as the default export.

It should be one of the coolest things I've ever seen. Have it have a search and profile login and almost every feature that is really nice in a header. It should be framer level quality.


And a final prompt:
Construct a React component named Dashboard that integrates the Header, Sidebar, MainContent, and Footer components. (These should all be imports) This component should:

State Management: Maintain a state variable activeTab (string) using React’s useState hook, defaulting to an initial value (e.g., 'dashboard').

State Propagation: Pass activeTab and a state update function (e.g., setActiveTab) to the Sidebar component via the onTabChange prop. Also pass activeTab to MainContent so that it knows which content to render.

Layout: Arrange the components using a responsive layout. Place the Header at the top, a flex container for the body with the Sidebar on the left and MainContent on the right, and the Footer at the bottom.

Styling: Use inline styles or CSS classes for basic layout structure (e.g., flexbox, grid). Export Dashboard as the default export.


reacted to wassemgtk's post with 👍 about 3 hours ago
replied to dal4933's post about 4 hours ago
replied to dal4933's post about 5 hours ago
view reply

Thank you. I tried to verify it, but the ONNX runtime would not recognize CUDA no matter what...
There are some known issues, but even if you get around them, it's no use. The details are written at the bottom of app.py. Of course, this space is CPU space, but it was impossible even with Zero GPU space.
https://huggingface.co/spaces/John6666/Projekt-test

reacted to davidberenstein1957's post with ❤️ about 19 hours ago
view post
Post
979
🚨 New Bonus Unit: Tracing & Evaluating Your Agent! 🚨

Learn how to transform your agent from a simple demo into a robust, reliable product ready for real users.

UNIT: https://huggingface.co/learn/agents-course/bonus-unit2/introduction

In this unit, you'll learn:
- Offline Evaluation – Benchmark and iterate your agent using datasets.
- Online Evaluation – Continuously track key metrics such as latency, costs, and user feedback.

Happy testing and improving!

Thanks Langfuse team!
reacted to dal4933's post with 👀 about 19 hours ago
view post
Post
783
Hi everyone! 👋

I'm trying to deploy my custom YOLOv8 model (converted to ONNX) for live webcam object detection on Hugging Face Spaces using a T4 GPU. My model has 2 classes and works locally, but I'm having trouble getting the deployment on Hugging Face Spaces to work properly.

Has anybody faced similiar problems? Would highly appreciate feedback on the matter.
<3
  • 7 replies
·
replied to dal4933's post about 19 hours ago
view reply

If we can understand the error message, you may be able to find a solution.
It is easy to investigate the cause if there is a sample Spaces, even if with the model before fine-tuning.
Since the Spaces of Hugging Face can be easily duplicated, we can debug and provide feedback.

reacted to openfree's post with 🔥 about 21 hours ago
view post
Post
2811
🚀 DeepSeek V3-0324 + Real-time Research Power! 🌐

Hello there! Today I'm excited to introduce an amazing tool based on the DeepSeek V3-0324 latest model. This isn't just another AI chatbot—it's a true "research assistant" capable of real-time information retrieval and analysis!

openfree/Deepseek-v3-0324-Research

🧠 Key Strengths of DeepSeek V3-0324
DeepSeek V3-0324, provided by Fireworks AI, comes with these powerful advantages:

🎯 Superior Reasoning: Excellent ability to solve complex problems step-by-step
📚 Extensive Knowledge: Deep understanding across various topics from comprehensive training

🧩 Context Awareness: Maintains long conversation contexts for consistent responses
🌍 Multilingual Support: Processes various languages effectively

🔎 Added Real-time "Deep Research" Capability!
The most exciting feature of this project is the implementation of real-time search functionality similar to ChatGPT's Browse with Bing or Perplexity AI! 🌟
How does it work?

📋 Query Analysis: Analyzes questions to automatically extract optimal search keywords
🌐 Web Search: Utilizes advanced search technology to retrieve the latest information
🧪 Result Analysis: Intelligently analyzes search results and evaluates relevance
💡 Comprehensive Response: Combines freshly retrieved information with AI's existing knowledge

Key Benefits:

⏱️ Up-to-date Information: Always provides the latest data through real-time web searches
📊 Enhanced Reliability: Improves trustworthiness by citing information sources
🔄 Overcoming Knowledge Limitations: Handles questions beyond the AI's training cutoff
🛠️ Research Efficiency: Processes everything from information retrieval to analysis in one go

🖥️ How to Use
It's simple! Just enable the "Deep Research" checkbox and ask your question. The AI will automatically search for and analyze relevant information to provide rich, informed answers.
  • 1 reply
·
reacted to MikeDoes's post with 🚀 about 21 hours ago
view post
Post
1615
🚀 We are quite excited to announce the Ai4Privacy Python library! 🎉

pip install ai4privacy to anonymize short english text with OpenPII Masking 500k labels

📊 Day 5/7 of PII Masking 1M announcements complete! ⏰
reacted to takarajordan's post with 🔥 about 21 hours ago
view post
Post
943
Takara takes 3rd place in the {tech:munich} AI hackathon with Fudeno!

A little over 2 weeks ago @aldigobbler and I set out to create the largest MultiModal SVG dataset ever created, we succeeded in this and when I was in Munich, Germany I took it one step further and made an entire app with it!

We fine-tuned Mistral Small, made a Next.JS application and blew some minds, taking 3rd place out of over 100 hackers. So cool!

If you want to see the dataset, please see below.

takara-ai/fudeno-instruct-4M
reacted to samchain's post with 👀 about 21 hours ago
view post
Post
328
NLP for Economics 1.2 is out !

This collection features two models:
- EconoSentiment : a first version based on econo-sentence-v2 and trained on the Financial PhraseBank, showcasing great performances.
- EconoDetect-US : a classifier to detect texts related to the US economy.

And two datasets:
- economics-relevance : the HF version of the Kaggle dataset US Economics News
- imf-weo-reports : A first version and gated dataset aggregating several World Economic Outlooks from the IMF
  • 1 reply
·
reacted to onekq's post with 🔥 about 21 hours ago
reacted to AdinaY's post with 🚀 1 day ago
reacted to etemiz's post with 👍 1 day ago
view post
Post
394
Mistral Small 3.1 numbers are in. It is interesting Mistral always lands in the middle.
https://sheet.zoho.com/sheet/open/mz41j09cc640a29ba47729fed784a263c1d08?sheetid=0&range=A1

I started to do the comparison with 2 models now. In the past Llama 3.1 70B Q4 was the one doing the comparison of answers. Now I am using Gemma 3 27B Q8 as well to have a second opinion on it. Gemma 3 produces very similar measurement to Llama 3.1. So the end result is not going to shake much.
  • 1 reply
·
reacted to Dragunflie-420's post with 👀 1 day ago
view post
Post
1460
Hello community. My name is nikki and I am looking to form a team for a serious project build platform/design/idea/project's...Ive been creating AI professional personas with custom skill sets and divisions of expertise. I want to create a viable business. Ive been working hard but i admit theres so much i do not have time to learn to do. Its taken me three years to learn enough to be here. I dont have a big set up in fact im cloud and ide space trial enterprise here and there all for space. I suck at execution and thats because I dont know how really. I need help from a person. AI has done all it can without hands. Im blabbering at this point. Have nothing big techy to say other than I build and ideate all day hmu glad to meet some like minded individuals ...seriously! Teach me leave me feeling confident in our collaborations not the need to build security software....poor attemt at hacking humor...im neither a comedian or hacker lol....full stacker yep:)
·