not sure tbh, IMO it makes more sense to apply for a community grant for a CPU upgrade as you need them, just blanket granting to an entire org isn't realistic
Adam Molnar PRO
lunarflu
AI & ML interests
trust and safety 🤗
reach out on discord (lunarflu) if you have any questions:
hf.co/discord/join
Recent Activity
upvoted
an
article
2 days ago
How To Build a News Agent with GPT-OSS, Hugging Face Inference & Gradio
upvoted
an
article
2 days ago
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
Organizations
replied to
nroggendorff's
post
6 days ago
reacted to
fdaudens's
post with 🤗🚀🔥
2 months ago
Post
1869
MCP just hit a tipping point:
- @hf .co made it dead simple: just type "hf.co/mcp" in your chat. No JSON wrestling, no config files.
- Meanwhile, OpenAI, Google, and Microsoft all adopted it as their standard.
https://huggingface.co/blog/fdaudens/mcp-ai-industry-standard
- @hf .co made it dead simple: just type "hf.co/mcp" in your chat. No JSON wrestling, no config files.
- Meanwhile, OpenAI, Google, and Microsoft all adopted it as their standard.
https://huggingface.co/blog/fdaudens/mcp-ai-industry-standard
- 1 reply
reacted to
openfree's
post with 🔥
3 months ago
Post
4299
🌊 CycleNavigator: Visualizing Economic and Political Cycles Through AI at a Glance! 🧠💹
💫 Strategic Intelligence Tool for Navigating Historical Waves and Forecasting the Future
Hello there! 🙌 CycleNavigator brings you an innovative fusion of economic history, data visualization, and generative AI. This open-source project revolutionizes decision-making by displaying four major economic and political cycles through interactive visualizations!
📊 Experience Four Major Cycles in One View:
Business Cycle (≈9 years) ⏱️ - The 'heartbeat' of investment and inventory
Kondratiev Wave (≈50 years) 🌐 - Long technological innovation waves
Finance Cycle (≈80 years) 💰 - Rhythm of debt and financial crises
Hegemony Cycle (≈250 years) 🏛️ - Transitions in global order
✨ Cutting-Edge Features:
Interactive Wave Visualization 🎯 - Intuitive graphs powered by Plotly
AI-Powered Historical Similarity Mapping 🧩 - Connecting past events via SBERT embeddings
Real-time News Integration 📰 - Linking current issues to long cycles with Brave API
GPT-Enhanced Analysis 🤖 - Delivering structured insights through optimized prompting
💡 Practical Applications:
Improve decision accuracy ⚡ by instantly grasping economic trends
Identify connections 🔄 between breaking news and long-term cycles
Gain reliable insights 🔍 through verifiable data and transparent methodology
Extend to multiple domains 🚀 - education, research, asset management, policy institutes
🌟 A New Intelligence Paradigm:
When slow cycles (9-50-80-250 years) and fast headlines (Brave API) meet on a single canvas, experience an innovative decision-making environment where you can reconstruct the past, interpret the present, and design future scenarios!
🔗 Open-Source Repository: openfree/Cycle-Navigator
🔗 Blog Article: https://huggingface.co/blog/openfree/cycle-navigator
👥 Join the Community: https://discord.gg/openfreeai
💫 Strategic Intelligence Tool for Navigating Historical Waves and Forecasting the Future
Hello there! 🙌 CycleNavigator brings you an innovative fusion of economic history, data visualization, and generative AI. This open-source project revolutionizes decision-making by displaying four major economic and political cycles through interactive visualizations!
📊 Experience Four Major Cycles in One View:
Business Cycle (≈9 years) ⏱️ - The 'heartbeat' of investment and inventory
Kondratiev Wave (≈50 years) 🌐 - Long technological innovation waves
Finance Cycle (≈80 years) 💰 - Rhythm of debt and financial crises
Hegemony Cycle (≈250 years) 🏛️ - Transitions in global order
✨ Cutting-Edge Features:
Interactive Wave Visualization 🎯 - Intuitive graphs powered by Plotly
AI-Powered Historical Similarity Mapping 🧩 - Connecting past events via SBERT embeddings
Real-time News Integration 📰 - Linking current issues to long cycles with Brave API
GPT-Enhanced Analysis 🤖 - Delivering structured insights through optimized prompting
💡 Practical Applications:
Improve decision accuracy ⚡ by instantly grasping economic trends
Identify connections 🔄 between breaking news and long-term cycles
Gain reliable insights 🔍 through verifiable data and transparent methodology
Extend to multiple domains 🚀 - education, research, asset management, policy institutes
🌟 A New Intelligence Paradigm:
When slow cycles (9-50-80-250 years) and fast headlines (Brave API) meet on a single canvas, experience an innovative decision-making environment where you can reconstruct the past, interpret the present, and design future scenarios!
🔗 Open-Source Repository: openfree/Cycle-Navigator
🔗 Blog Article: https://huggingface.co/blog/openfree/cycle-navigator
👥 Join the Community: https://discord.gg/openfreeai
reacted to
Kseniase's
post with 👍🤝
3 months ago
Post
3279
7 Free resources to master Multi-Agent Systems (MAS)
Collective intelligence is the future of AI. Sometimes, a single agent isn't enough — a team of simpler, specialized agents working together to solve a task can be a much better option. Building Multi-Agent Systems (MAS) isn’t easy, that's why today we’re offering you a list of sources that may help you master MAS:
1. CrewAI tutorials -> https://docs.crewai.com/introduction#ready-to-start-building%3F
At the end of the page you'll find a guide on how to build a crew of agents that research and analyze a topic, and create a report. Also, there are useful guides on how to build a single CrewAI agent and a workflow
2. Building with CAMEL multi-agent framework -> https://github.com/camel-ai/camel
Offers guides, cookbooks and other useful information to build even million agent societies, explore and work with MAS
3. Lang Chain multi-agent tutorial -> https://langchain-ai.github.io/langgraph/agents/multi-agent/
Explains how to make agents communicate via handoffs pattern on the example of 2 multi-agent architectures - supervisor and swarm
4. "Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations" by Yoav Shoham and Kevin Leyton-Brown -> https://www.masfoundations.org/download.html
This book explains learning between agents, how multiple agents solve shared problems and communicate with focus on theory, practical examples and algorithms, diving into the game theory and logical approaches
Also, check out The Turing Post article about MAS -> https://www.turingpost.com/p/mas
Our article can be a good starting guide for you to explore what MAS is, its components, architectures, types, top recent developments and current trends
More resources in the comments 👇
If you liked it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
Collective intelligence is the future of AI. Sometimes, a single agent isn't enough — a team of simpler, specialized agents working together to solve a task can be a much better option. Building Multi-Agent Systems (MAS) isn’t easy, that's why today we’re offering you a list of sources that may help you master MAS:
1. CrewAI tutorials -> https://docs.crewai.com/introduction#ready-to-start-building%3F
At the end of the page you'll find a guide on how to build a crew of agents that research and analyze a topic, and create a report. Also, there are useful guides on how to build a single CrewAI agent and a workflow
2. Building with CAMEL multi-agent framework -> https://github.com/camel-ai/camel
Offers guides, cookbooks and other useful information to build even million agent societies, explore and work with MAS
3. Lang Chain multi-agent tutorial -> https://langchain-ai.github.io/langgraph/agents/multi-agent/
Explains how to make agents communicate via handoffs pattern on the example of 2 multi-agent architectures - supervisor and swarm
4. "Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations" by Yoav Shoham and Kevin Leyton-Brown -> https://www.masfoundations.org/download.html
This book explains learning between agents, how multiple agents solve shared problems and communicate with focus on theory, practical examples and algorithms, diving into the game theory and logical approaches
Also, check out The Turing Post article about MAS -> https://www.turingpost.com/p/mas
Our article can be a good starting guide for you to explore what MAS is, its components, architectures, types, top recent developments and current trends
More resources in the comments 👇
If you liked it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
- 2 replies
reacted to
m-ric's
post with 🤗🔥
3 months ago
Post
4509
I've made an open version of Google's NotebookLM, and it shows the superiority of the open source tech task! 💪
The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.
The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.
And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.
Overall, open source solutions rival the quality of closed-source solutions at close to no cost!
Try it here 👉👉 m-ric/open-notebooklm
The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.
The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.
And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.
Overall, open source solutions rival the quality of closed-source solutions at close to no cost!
Try it here 👉👉 m-ric/open-notebooklm
- 3 replies
reacted to
merve's
post with ❤️🔥👍🚀
4 months ago
Post
6635
A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥
D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩
> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352
Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩
Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️
D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩
Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️
this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.
D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩
> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352
Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩
Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️
D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩
Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️
this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.
- 2 replies
reacted to
onekq's
post with 🔥
4 months ago
Post
2007
AxB stand for Approximately xB or Activating xB (for a Mixture-of-Expert model), this is really interesting naming 😅
Qwen/Qwen3-235B-A22B
Qwen/Qwen3-30B-A3B
Qwen/Qwen3-235B-A22B
Qwen/Qwen3-30B-A3B
- 1 reply
reacted to
anakin87's
post with 👍
4 months ago
Post
3500
𝗜 𝘁𝗿𝗮𝗶𝗻𝗲𝗱 𝗮 𝗟𝗮𝗻𝗴𝘂𝗮𝗴𝗲 𝗠𝗼𝗱𝗲𝗹 𝘁𝗼 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗲𝘃𝗲𝗻𝘁𝘀 𝘄𝗶𝘁𝗵 𝗚𝗥𝗣𝗢! 👑 🗓️
✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo
I experimented with GRPO lately.
I am fascinated by models learning from prompts and rewards - no example answers needed like in Supervised Fine-Tuning.
After the DeepSeek boom, everyone is trying GRPO with GSM8K or the Countdown Game...
I wanted a different challenge, like 𝘁𝗲𝗮𝗰𝗵𝗶𝗻𝗴 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗳𝗿𝗼𝗺 𝗮 𝗹𝗶𝘀𝘁 𝗼𝗳 𝗲𝘃𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗽𝗿𝗶𝗼𝗿𝗶𝘁𝗶𝗲𝘀.
Choosing an original problem forced me to:
🤔 Think about the problem setting
🧬 Generate data
🤏 Choose the right base model
🏆 Design reward functions (and experiencing reward hacking)
🔄 Run multiple rounds of training, hoping that my model would learn something.
A fun and rewarding 😄 experience.
I learned a lot of things, that I want to share with you. 👇
✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo
💻 Code: https://github.com/anakin87/qwen-scheduler-grpo
🤗 Hugging Face collection (dataset and model): anakin87/qwen-scheduler-grpo-680bcc583e817390525a8837
✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo
I experimented with GRPO lately.
I am fascinated by models learning from prompts and rewards - no example answers needed like in Supervised Fine-Tuning.
After the DeepSeek boom, everyone is trying GRPO with GSM8K or the Countdown Game...
I wanted a different challenge, like 𝘁𝗲𝗮𝗰𝗵𝗶𝗻𝗴 𝗮 𝗺𝗼𝗱𝗲𝗹 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗰𝗵𝗲𝗱𝘂𝗹𝗲 𝗳𝗿𝗼𝗺 𝗮 𝗹𝗶𝘀𝘁 𝗼𝗳 𝗲𝘃𝗲𝗻𝘁𝘀 𝗮𝗻𝗱 𝗽𝗿𝗶𝗼𝗿𝗶𝘁𝗶𝗲𝘀.
Choosing an original problem forced me to:
🤔 Think about the problem setting
🧬 Generate data
🤏 Choose the right base model
🏆 Design reward functions (and experiencing reward hacking)
🔄 Run multiple rounds of training, hoping that my model would learn something.
A fun and rewarding 😄 experience.
I learned a lot of things, that I want to share with you. 👇
✍️ Blog post: https://huggingface.co/blog/anakin87/qwen-scheduler-grpo
💻 Code: https://github.com/anakin87/qwen-scheduler-grpo
🤗 Hugging Face collection (dataset and model): anakin87/qwen-scheduler-grpo-680bcc583e817390525a8837
- 2 replies
reacted to
julien-c's
post with 😎👍🚀🔥
4 months ago
Post
4105
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.
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.
- 9 replies
reacted to
as-cle-bert's
post with 🤗
4 months ago
Post
3024
Finding a job that matches with our resume shouldn't be difficult, especially now that we have AI... And still, we're drowning in unclear announcements, jobs whose skill requirements might not really fit us, and tons of material😵💫
That's why I decided to build 𝐑𝐞𝐬𝐮𝐦𝐞 𝐌𝐚𝐭𝐜𝐡𝐞𝐫 (https://github.com/AstraBert/resume-matcher), a fully open-source application that scans your resume and searches the web for jobs that match with it!🎉
The workflow is very simple:
🦙 A LlamaExtract agent parses the resume and extracts valuable data that represent your profile
🗄️The structured data are passed on to a Job Matching Agent (built with LlamaIndex😉) that uses them to build a web search query based on your resume
🌐 The web search is handled by Linkup, which finds the top matches and returns them to the Agent
🔎 The agent evaluates the match between your profile and the jobs, and then returns a final answer to you
So, are you ready to find a job suitable for you?💼 You can spin up the application completely locally and with Docker, starting from the GitHub repo ➡️ https://github.com/AstraBert/resume-matcher
Feel free to leave your feedback and let me know in the comments if you want an online version of Resume Matcher as well!✨
That's why I decided to build 𝐑𝐞𝐬𝐮𝐦𝐞 𝐌𝐚𝐭𝐜𝐡𝐞𝐫 (https://github.com/AstraBert/resume-matcher), a fully open-source application that scans your resume and searches the web for jobs that match with it!🎉
The workflow is very simple:
🦙 A LlamaExtract agent parses the resume and extracts valuable data that represent your profile
🗄️The structured data are passed on to a Job Matching Agent (built with LlamaIndex😉) that uses them to build a web search query based on your resume
🌐 The web search is handled by Linkup, which finds the top matches and returns them to the Agent
🔎 The agent evaluates the match between your profile and the jobs, and then returns a final answer to you
So, are you ready to find a job suitable for you?💼 You can spin up the application completely locally and with Docker, starting from the GitHub repo ➡️ https://github.com/AstraBert/resume-matcher
Feel free to leave your feedback and let me know in the comments if you want an online version of Resume Matcher as well!✨
- 2 replies