PASD isn’t recent, but still delivers strong results — worth restoring rather than replacing.
Getting it to run again wasn’t a simple dependency issue. It relied on parts of diffusers that no longer exist, while moving to Gradio 6 forced a much newer HF stack — and I couldn’t modify the original source directly.
Recreating the old environment wasn’t practical. So I patched the downloaded code at runtime before import and made it compatible with today’s stack.
That ended up being the only approach that held without forking or freezing everything to outdated versions.
If you’ve used it before (or are curious), feel free to give it another try.
The Qwen3.5 Multimodal Understanding Demo, powered by Qwen3.5-2B, is now available on HF Spaces! It is a lightweight model designed for fast image and video reasoning. Built with Gradio, the demo showcases Image QA, Video QA, object detection, and 2D point tracking, along with real-time token streaming.
🚀 I built a Multimodal Vision-Language Model from using Gemma-270M + CLIP!
Just finished training my multimodal model on the full LLaVA-Instruct-150K dataset (157K samples) and wanted to share the results!
🔧 What I Built: A vision-language model that can understand images and answer questions about them, combining: - Google Gemma-3-270M (language) - OpenAI CLIP ViT-Large/14 (vision) - LoRA fine-tuning for efficiency
📊 Training Stats: - 157,712 training samples (full LLaVA dataset) - 3 epochs on A100 40GB - ~9 hours training time - Final loss: 1.333 training / 1.430 validation - Only 18.6M trainable params (3.4% of 539M total)
📈 sagar007/multigemma Benchmark Results: - VQA Accuracy: 53.8% - Works great for: animal detection, room identification, scene understanding
fine-tuning a 14B model with TRL + SFT on a free Colab (T4 GPU)? thanks to the latest TRL optimizations, you actually can! sharing a new notebook showing how to do it 😎
If your Space stops working after restarting mainly for the last 5 days (https://discuss.huggingface.co/t/my-space-suddenly-went-offline-the-cpu-cannot-restart/151121/22), try some of following. 1. Add pydantic==2.10.6 to requirements.txt or upgrade Gradio to the latest version. 2. Upgrade PyTorch to 2.2.0 or later (torch>=2.2.0 for Zero GPU space). 3. Fix Transformers to 4.49.0 or earlier (transformers<=4.49.0for spaces using Transformers or Diffusers). 4. Fix huggingface_hub to the old version (huggingface_hub==0.25.2 for if an error like cached_download is not available occurs or inference does not work properly) 5. Specifying WORKDIR in Dockerfile may cause the application to fail to start with error 137. (Docker Spaces, https://discuss.huggingface.co/t/error-code-137-cache-error/152177)
Edit: Zero GPU space has been upgraded from A100 to H200. This is likely the reason why older versions of PyTorch are no longer supported. In fact, an error message to that effect was displayed. zero-gpu-explorers/README#163
Multilingual Tokenization Showdown Analyzing 12 LLM Tokenizers Across 204 Languages.
First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages: Norod78/WikiCat-Multilingual
For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language).
I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo: https://github.com/Norod/wikicat-tokenizer-eval
Introducing AWQ and GPTQ quantized versions of SmolVLM from Hugging Face!
These models only had their text models quantized, and had a 50% model size reduction (4GB~2GB) while keeping model degradation under 1% on the DocVQA benchmark.
Finally, I uploaded the model I developed for my master’s thesis! Given a financial event, it provides explained predictions based on a dataset of past news and central bank speeches. Try it out here: SelmaNajih001/StockPredictionExplanation (Just restart the space and wait a minute)
🛠 Technical Implementation: (Runnable with Copy & Paste at the MLange link!)
📊 Device Compatibility Matrix: Tested on 50+ devices including Samsung Galaxy series, Google Pixel lineup, and Xiaomi devices, iPhones and iPads. Consistent sub-5ms performance across the board!
🚀 Applications Unlocked: - Real-time AR/VR face tracking - Privacy-preserving edge authentication - Live video processing pipelines - Mobile security applications - Interactive camera filters
The democratization of high-performance computer vision on mobile devices is happening NOW! This study proves that complex CV models can run efficiently on consumer hardware without compromising accuracy. Want to reproduce these results? Check out the benchmark methodology and implementation guide!
PawMatchAI — Now with SBERT-Powered Recommendations! 🐶✨
⭐️ NEW: Description-based recommendations are here! Just type in your lifestyle or preferences (e.g. “I live in an apartment and want a quiet dog”), and PawMatchAI uses SBERT semantic embeddings to understand your needs and suggest compatible breeds.
What can PawMatchAI do today? 📸 Upload a photo to identify your dog from 124 breeds with detailed info. ⚖️ Compare two breeds side-by-side, from grooming needs to health insights. 📊 Visualize breed traits with radar and comparison charts. 🎨 Try Style Transfer to turn your dog’s photo into anime, watercolor, cyberpunk, and more.
What’s next? 🎯 More fine-tuned recommendations. 📱 Mobile-friendly deployment. 🐾 Expansion to additional species.
My goal: To make breed discovery not only accurate but also interactive and fun — combining computer vision, semantic understanding, and creativity to help people find their perfect companion.
Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯 Demo (+ source code): webml-community/DINOv3-video-tracking
This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍
How does it work? 🤔 1️⃣ Generate and cache image features for each frame 2️⃣ Create a list of embeddings for selected patch(es) 3️⃣ Compute cosine similarity between each patch and the selected patch(es) 4️⃣ Highlight those whose score is above some threshold
... et voilà! 🥳
You can also make selections across frames to improve temporal consistency! This is super useful if the object changes its appearance slightly throughout the video.
