Victor Mustar PRO

victor

AI & ML interests

Building the UX of this website

Recent Activity

Articles

Organizations

victor's activity

Reacted to LukeNeumann's post with 👀 about 14 hours ago
view post
Post
599
I had a question about Trending datasets. Our initial dataset "Oregon Coast in 4K" was trending at #3 for video at about 700 downloads.

Over the past two days our downloads have spiked, now up to over 2,000, but the dataset has dropped down to the 3rd or 4th page of Trending.

What metrics are used to determine dataset Trending position?
  • 1 reply
·
Reacted to merve's post with ❤️ 1 day ago
view post
Post
2747
your hugging face profile now has your recent activities 🤗
Reacted to jsulz's post with 👀 1 day ago
view post
Post
877
Something I love about working at Hugging Face is the opportunity to design and work in public. Right now, we’re redesigning the architecture that supports uploads and downloads on the Hub.

Datasets and models are growing fast, and so are the challenges of storing and transferring them efficiently. To keep up, we're introducing a new protocol for uploads and downloads, supported by a content-addressed store (CAS).

Here’s what’s coming:

📦 Smarter uploads: Chunk-level management enables advanced deduplication, compression, and reduces redundant transfers, speeding up uploads.
⚡ Efficient downloads: High throughput and low latency ensure fast access, even during high-demand model releases.
🔒 Enhanced security: Validate uploads before storage to block malicious or invalid data.

We analyzed 24 hours of global upload activity in October (88 countries, 130TB of data!) to design a system that scales with your needs.

The result? A proposed infrastructure with CAS nodes in us-east-1, eu-west-3, and ap-southeast-1.

🔗 Read the blog post for the full details: https://huggingface.co/blog/rearchitecting-uploads-and-downloads

🌟 Check out our interactive demo to explore the data yourself!
xet-team/cas-analysis

We’d love to hear your feedback - let us know if you have questions or want to see more.
·
Reacted to gabrielchua's post with 👀 1 day ago
view post
Post
1003
Sharing my first paper!

==
Large Language Models (LLMs) are powerful, but they're prone to off-topic misuse, where users push them beyond their intended scope. Think harmful prompts, jailbreaks, and misuse. So how do we build better guardrails?

Traditional guardrails rely on curated examples or classifiers. The problem?
⚠️ High false-positive rates
⚠️ Poor adaptability to new misuse types
⚠️ Require real-world data, which is often unavailable during pre-production

Our method skips the need for real-world misuse examples. Instead, we:
1️⃣ Define the problem space qualitatively
2️⃣ Use an LLM to generate synthetic misuse prompts
3️⃣ Train and test guardrails on this dataset

We apply this to the off-topic prompt detection problem, and fine-tune simple bi- and cross-encoder classifiers that outperform heuristics based on cosine similarity or prompt engineering.

Additionally, framing the problem as prompt relevance allows these fine-tuned classifiers to generalise to other risk categories (e.g., jailbreak, toxic prompts).

Through this work, we also open-source our dataset (2M examples, ~50M+ tokens) and models.

paper: A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection (2411.12946)

artifacts: govtech/off-topic-guardrail-673838a62e4c661f248e81a4
Reacted to csabakecskemeti's post with 👀 1 day ago
Reacted to maxiw's post with 👍 1 day ago
view post
Post
1602
You can now try out computer use models from the hub to automate your local machine with https://github.com/askui/vision-agent. 💻

import time
from askui import VisionAgent

with VisionAgent() as agent:
    agent.tools.webbrowser.open_new("http://www.google.com")
    time.sleep(0.5)
    agent.click("search field in the center of the screen", model_name="Qwen/Qwen2-VL-7B-Instruct")
    agent.type("cats")
    agent.keyboard("enter")
    time.sleep(0.5)
    agent.click("text 'Images'", model_name="AskUI/PTA-1")
    time.sleep(0.5)
    agent.click("second cat image", model_name="OS-Copilot/OS-Atlas-Base-7B")


Currently these models are integrated with Gradio Spaces API. Also planning to add local inference soon!

Currently supported:
- Qwen/Qwen2-VL-7B-Instruct
- Qwen/Qwen2-VL-2B-Instruct
- AskUI/PTA-1
- OS-Copilot/OS-Atlas-Base-7B
  • 2 replies
·
Reacted to KnutJaegersberg's post with 🔥 1 day ago
Reacted to davanstrien's post with ❤️ 1 day ago
view post
Post
1356
First dataset for the new Hugging Face Bluesky community organisation: bluesky-community/one-million-bluesky-posts 🦋

📊 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗

Excited to see people build more open tools for a more open social media platform!
Reacted to vilarin's post with 🤗🤯 1 day ago
view post
Post
891
A few days ago, Blackforestlabs released FLUX.1 Tools, which has surprised everyone with its quality and effects. Now that diffusers support these features, you can easily deploy and build your own Tools.
Combined with the powerful Gradio and ZeroGPU, you can experience the Tools immediately, which is truly wonderful.
I was impressed by the Flux.1 Fill dev, so here I've built a demo for it, making it easy to use for inpainting and outpainting images.

🏄Model: black-forest-labs/FLUX.1-Fill-dev
🦖Demo: vilarin/Flux.1-Fill-dev
👏diffusers: https://github.com/huggingface/diffusers/tree/main/src/diffusers/pipelines/flux
Reacted to vansin's post with 😔 1 day ago
view post
Post
863
Amazing !!!! test Post
Reacted to fdaudens's post with 👀 2 days ago
view post
Post
1240
🤖 93% of Gen Z workers use AI tools weekly, but nearly half of all workers aren't comfortable admitting it. The tech adoption gap isn't about usage—it's about openness. Why are we still treating AI tools like a workplace secret? 🤔

See this article: https://www.axios.com/2024/11/25/gen-z-ai-work-survey
  • 1 reply
·
Reacted to clem's post with 🚀 2 days ago
view post
Post
1749
I've been in Brazil for 10 days now 🇧🇷🇧🇷🇧🇷

I've been surprised by the gap between the massive number of people interested in AI (chatgpt adoption is crazy here) and the relatively low number of real AI builders - aka people and companies building their own AI models, datasets and apps.

Lots of efforts needed across the world for everyone to participate, control and benefit this foundational technology, starting with open-source & multi-lingual AI, more access to GPUs & AI builder training for all!
Reacted to prithivMLmods's post with 🔥 2 days ago
Reacted to openfree's post with 🔥 2 days ago
view post
Post
2832
🤗 HuggingFace Trending TOP 300 Board - Featuring AI Rating System
📊 Service Introduction
A comprehensive dashboard that provides at-a-glance access to the real-time TOP 300 trending Spaces, Models, and Datasets on HuggingFace.
Our specially developed AI rating system evaluates the practical value and growth potential of each item.
⭐ Key Features
1. AI Rising Rate

Growth potential evaluation based on creation date and ranking
5-tier star rating system (★★★★★)
Evaluation Criteria:

Recency: Higher relative weights for recently created items
Ranking Impact: Higher relative weights for top rankings
Comprehensive assessment using statistical/analytical models applied to AI



2. AI Popularity Score

Comprehensive evaluation combining objective popularity and Rising Rate
18-tier grading system from AAA+ to B-
Evaluation Elements:

Base Score: Benchmark based on likes, downloads, comments, etc.
Additional Score: Rising Rate applied as a weighted factor
Comprehensive assessment using statistical/analytical models applied to AI



3. Visualization Features

Real-time screenshot capture with caching
Intuitive card-based UI
Responsive grid layout
Pastel gradient design

🎯 Applications

AI/ML Project Trend Analysis
Early Discovery of Promising Models/Datasets
Community Activity Monitoring
Research/Development Direction Reference

💡 Key Advantages

Real-time TOP 300 ranking
AI-based objective evaluation system
Fast loading with caching system
Intuitive and modern UI/UX
Integrated dashboard for 3 categories

🔄 Update Cycle

Real-time data reflection
Manual refresh option
Minimized server load through screenshot caching

🎁 Future Plans

Addition of detailed analysis report feature
Custom filtering options
Time-series trend analysis
Category-specific detailed statistics

🌐 How to Access
openfree/trending-board

#HuggingFace #AI #MachineLearning #TrendingBoard #DataScience #
  • 3 replies
·
Reacted to luigi12345's post with 👀 3 days ago
view post
Post
3521
MinimalScrap
Only Free Dependencies. Save it.It is quite useful uh.


!pip install googlesearch-python requests
from googlesearch import search
import requests
query = "Glaucoma"
for url in search(f"{query} site:nih.gov filetype:pdf", 20):
    if url.endswith(".pdf"):
        with open(url.split("/")[-1], "wb") as f: f.write(requests.get(url).content)
        print("✅" + url.split("/")[-1])
print("Done!")

Reacted to vincentg64's post with 👍 3 days ago
view post
Post
1149
There is no such thing as a Trained LLM https://mltblog.com/3CEJ9Pt

What I mean here is that traditional LLMs are trained on tasks irrelevant to what they will do for the user. It’s like training a plane to efficiently operate on the runway, but not to fly. In short, it is almost impossible to train an LLM, and evaluating is just as challenging. Then, training is not even necessary. In this article, I dive on all these topics.

➡️ Training LLMs for the wrong tasks

Since the beginnings with Bert, training an LLM typically consists of predicting the next tokens in a sentence, or removing some tokens and then have your algorithm fill the blanks. You optimize the underlying deep neural networks to perform these supervised learning tasks as well as possible. Typically, it involves growing the list of tokens in the training set to billions or trillions, increasing the cost and time to train. However, recently, there is a tendency to work with smaller datasets, by distilling the input sources and token lists. After all, out of one trillion tokens, 99% are noise and do not contribute to improving the results for the end-user; they may even contribute to hallucinations. Keep in mind that human beings have a vocabulary of about 30,000 keywords, and that the number of potential standardized prompts on a specialized corpus (and thus the number of potential answers) is less than a million.

➡️ Read the full articles at https://mltblog.com/3CEJ9Pt, also featuring issues with evaluation metrics and the benefits of untrained LLMs.
Reacted to prithivMLmods's post with 🤗 3 days ago
view post
Post
3865
CRISP 🔥 [ Isometric-3D-Cinematography / Isometric-3D-Obj / 3D-Kawaii / Long Toons ]

[ Flux DLC ] : prithivMLmods/FLUX-LoRA-DLC

[ Stranger Zone ] : https://huggingface.co/strangerzonehf

🎃[ Isometric 3D Cinematography ] : strangerzonehf/Flux-Isometric-3D-Cinematography
🎃[ Isometric 3D ] : strangerzonehf/Flux-Isometric-3D-LoRA
🎃[ Cute 3D Kawaii ] : strangerzonehf/Flux-Cute-3D-Kawaii-LoRA
🌚[ Long Toon 3D ] : prithivMLmods/Flux-Long-Toon-LoRA

[ Stranger Zone Collection ] : prithivMLmods/stranger-zone-collections-6737118adcf2cb40d66d0c7e

[ Flux Collection ] : prithivMLmods/flux-lora-collections-66dd5908be2206cfaa8519be

[ Flux Mix ] : prithivMLmods/Midjourney-Flux

.
.
.
@prithivMLmods
Reacted to etemiz's post with 🤝 3 days ago
Reacted to cschroeder's post with 👀 3 days ago
view post
Post
1039
🐣 New release: small-text v2.0.0.dev1

With small language models on the rise, the new version of small-text has been long overdue! Despite the generative AI hype, many real-world tasks still rely on supervised learning—which is reliant on labeled data.

Highlights:
- Four new query strategies: Try even more combinations than before.
- Vector indices integration: HNSW and KNN indices are now available via a unified interface and can easily be used within your code.
- Simplified installation: We dropped the torchtext dependency and cleaned up a lot of interfaces.

Github: https://github.com/webis-de/small-text

👂 Try it out for yourself! We are eager to hear your feedback.
🔧 Share your small-text applications and experiments in the newly added showcase section.
🌟 Support the project by leaving a star on the repo!

#activelearning #nlproc #machinelearning