Jason Xu

Cloudy-Boom

boyingxu

AI & ML interests

Using ML for Data-Driven Attribution

Recent Activity

reacted to sondhiArm's post with 🔥 17 days ago

At Arm, we’re trying something a bit different - a new series of live code-alongs and Q&A sessions led by our engineers to support developers building, optimizing, and deploying cloud-native applications. https://www.arm.com/resources/webinar/code-along-arm-cloud-migration There are four live code-alongs, each followed by a “Connect with the Experts” session one week later. The first two sessions focus on using Hugging Face with Arm: • Apr 22: Build a RAG app with vector search and LLMs, optimized for Arm • Apr 30: Run LLaMA with PyTorch on Arm-based infrastructure If you're interested in the topics, you can sign up for one or more sessions. Each session includes time to ask questions directly to the Arm team.

reacted to yjernite's post with 🔥 19 days ago

Today in Privacy & AI Tooling - introducing a nifty new tool to examine where data goes in open-source apps on 🤗 HF Spaces have tons (100Ks!) of cool demos leveraging or examining AI systems - and because most of them are OSS we can see exactly how they handle user data 📚🔍 That requires actually reading the code though, which isn't always easy or quick! Good news: code LMs have gotten pretty good at automatic review, so we can offload some of the work - here I'm using https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct to generate reports and it works pretty OK 🙌 The app works in three stages: 1. Download all code files 2. Use the Code LM to generate a detailed report pointing to code where data is transferred/(AI-)processed (screen 1) 3. Summarize the app's main functionality and data journeys (screen 2) 4. Build a Privacy TLDR with those inputs It comes with a bunch of pre-reviewed apps/Spaces, great to see how many process data locally or through (private) HF endpoints 🤗 Note that this is a POC, lots of exciting work to do to make it more robust, so: - try it: https://huggingface.co/spaces/yjernite/space-privacy - reach out to collab: https://huggingface.co/spaces/yjernite/space-privacy/discussions

reacted to JLouisBiz's post with 🤝 23 days ago

**Video**: https://www.youtube.com/watch?v=jRKRsGsLfW0 **Integrating large language model with file manager to describe your illegally downloaded movies.** When you have a bunch of movies downloaded by Torrent, you maybe want a description and description is missing. This video shows how you can use the script to invoke the large language model. And then you get a description of a movie in a second or three.

View all activity

Organizations

None yet

Cloudy-Boom's activity

reacted to sondhiArm's post with 🔥 17 days ago

Post

1083

At Arm, we’re trying something a bit different - a new series of live code-alongs and Q&A sessions led by our engineers to support developers building, optimizing, and deploying cloud-native applications.

https://www.arm.com/resources/webinar/code-along-arm-cloud-migration

There are four live code-alongs, each followed by a “Connect with the Experts” session one week later.

The first two sessions focus on using Hugging Face with Arm:
• Apr 22: Build a RAG app with vector search and LLMs, optimized for Arm
• Apr 30: Run LLaMA with PyTorch on Arm-based infrastructure

If you're interested in the topics, you can sign up for one or more sessions. Each session includes time to ask questions directly to the Arm team.

reacted to yjernite's post with 🔥 19 days ago

Post

3167

Today in Privacy & AI Tooling - introducing a nifty new tool to examine where data goes in open-source apps on 🤗

HF Spaces have tons (100Ks!) of cool demos leveraging or examining AI systems - and because most of them are OSS we can see exactly how they handle user data 📚🔍

That requires actually reading the code though, which isn't always easy or quick! Good news: code LMs have gotten pretty good at automatic review, so we can offload some of the work - here I'm using Qwen/Qwen2.5-Coder-32B-Instruct to generate reports and it works pretty OK 🙌

The app works in three stages:
1. Download all code files
2. Use the Code LM to generate a detailed report pointing to code where data is transferred/(AI-)processed (screen 1)
3. Summarize the app's main functionality and data journeys (screen 2)
4. Build a Privacy TLDR with those inputs

It comes with a bunch of pre-reviewed apps/Spaces, great to see how many process data locally or through (private) HF endpoints 🤗

Note that this is a POC, lots of exciting work to do to make it more robust, so:
- try it: yjernite/space-privacy
- reach out to collab: yjernite/space-privacy

reacted to JLouisBiz's post with 🤝 23 days ago

Post

3252

**Video**: https://www.youtube.com/watch?v=jRKRsGsLfW0

**Integrating large language model with file manager to describe your illegally downloaded movies.**

When you have a bunch of movies downloaded by Torrent, you maybe want a description and description is missing. This video shows how you can use the script to invoke the large language model. And then you get a description of a movie in a second or three.

liked a model 27 days ago

GSAI-ML/LLaDA-8B-Instruct

Text Generation • Updated Feb 27 • 101k • 251

liked a Space about 1 month ago

817

UGI Leaderboard

📢

Uncensored General Intelligence Leaderboard

replied to thomwolf's post about 1 month ago

just had my wife try it and she's now a developer 🤣

reacted to thomwolf's post with ❤️ about 1 month ago

Post

3323

The new DeepSite space is really insane for vibe-coders
enzostvs/deepsite

With the wave of vibe-coding-optimized LLMs like the latest open-source DeepSeek model (version V3-0324), you can basically prompt out-of-the-box and create any app and game in one-shot.

It feels so powerful to me, no more complex framework or under-the-hood prompt engineering to have a working text-to-app tool.

AI is eating the world and *open-source* AI is eating AI itself!

PS: and even more meta is that the DeepSite app and DeepSeek model are both fully open-source code => time to start recursively improve?

PPS: you still need some inference hosting unless you're running the 600B param model at home, so check the very nice list of HF Inference Providers for this model: deepseek-ai/DeepSeek-V3-0324

1 reply