Hugging Face's logo
Activity Feed Request to join this org

AI & ML interests

The Fellowship is a network of exceptional people from different backgrounds who contribute to open-source machine learning 🧙‍♂️🦸‍♀️🦹🧝‍♂️

Recent Activity
tomaarsen  submitted a paper 9 days ago
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
woojun-jung  authored a paper 6 months ago
QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answering
mariagrandury  authored a paper 9 months ago
BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data
View all activity
fffiloni 
posted an update 4 days ago
view post
Post
222
I’ve been building IDOL Commons 🗿

A place to create, share and explore 3D Gaussian splats, powered by IDOL from Sperid Labs.

Start with an image, or generate one from a prompt. Inspect the result in 3D, choose its thumbnail, add a description and credits, then decide whether to publish it to the community collection.

Browse what others have shared and download the original PLY files, with attribution and per-object licensing.

I’d love to see what you contribute — and hear what would make this useful in your workflow.

Try it:
fffiloni/idol-commons

Community dataset:
fffiloni/idol-community-assets
prithivMLmods 
posted an update 4 days ago
view post
Post
5,000
VIGOR (Vision Intelligence and Guardrail Oriented Reasoning) is now available on the Hugging Face Model Hub. It is a multimodal vision classification model based on Qwen3.5, designed for visual content-safety analysis and conservative classification, with a particular focus on identifying potentially sensitive content.

📦 Models: 27B, 9B, 4B —

prithivMLmods/VIGOR-27B,
prithivMLmods/VIGOR-flash,
prithivMLmods/VIGOR-mini

↗️ Collection:
https://huggingface.co/collections/prithivMLmods/vigor

To learn more, visit the app page or the respective model pages.
tomaarsen 
submitted a paper to Daily Papers 9 days ago
fffiloni 
posted an update 13 days ago
view post
Post
2,798
Carbon-X brings DNA and language together: it reads sequences and answers questions about them 🧬

To accompany the release article, I put together Carbon-X Playground: five experiments exploring sequence completion, single-letter changes, regulatory roles, DNA origins and motif finding.

Try curated samples or your own sequences, ask questions and compare answers with references when available.

Built with Gradio, running on ZeroGPU.

📖 HuggingFaceBio/Carbon-X-Release
🧬 fffiloni/Carbon-X-Playground
prithivMLmods 
posted an update 13 days ago
view post
Post
1,009
Flux-3-Image-Klein-LoRAs-Fast is now live on Hugging Face Spaces.🤗🔥

Plug and play with any custom LoRAs based on flux-3-image-klein. 16-step distilled fast inference, with support for prompt upsampling. More LoRAs will be added in the coming days!

🔗 Space: prithivMLmods/flux-3-image-klein-loras-fast

🔗 Image Generation Apps Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/flux-3-image-klein-loras-fast

To learn more, visit the app page or the respective model pages.
fffiloni 
posted an update 25 days ago
view post
Post
461
📖 A gamebook you can play in your own words, powered by local Decision Models.

Traditional gamebooks offer explicit branches: “To enter the forest, turn to page 42.” In Choose your own adventure, you can describe an action, question a character, or ask what you already know before deciding. Clickable choices remain available.

The story’s branches and consequences are authored. Natural language adds a flexible way to interact with them, with conversations between actions.

I built this project to explore a concrete role for Decision Models in an interactive application:

• Kev-4B makes structured decisions: matching intentions to available actions and distinguishing acting from discussing.
• Ink manages story progression, discoveries, inventory and endings.
• Qwen3-8B selects dialogue responses from authored content available in the current state.

Both models run locally inside the Space through llama.cpp, using quantized GGUFs. You can inspect the model calls, scores and routing decisions directly in the interface.

The current release includes three adventures in French and English, with a pack format for adding new stories without changing the engine.

It’s still experimental, and interpretations can go wrong. I’d love feedback on how it feels to play—and on this use of Decision Models to connect natural language with explicit game logic.

Try and play here: fffiloni/choose-your-own-adventure-dm 🤗
  • 1 reply
·
prithivMLmods 
posted an update about 1 month ago
view post
Post
4,772
OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!

🤗 Space: prithivMLmods/OneDecision-VisionGuard-Demo

This demo showcases the OneDecision-VisionGuard family of multimodal image classification models for detecting NSFW and other sensitive visual content, with structured JSON reasoning, improved accuracy, and better handling of edge cases such as sensitive imagery, uncensored analysis, scene descriptions, and classification reasoning.

📦 Models: 27B, 9B, 4B — prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT

↗️ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard

To learn more, visit the app page or the respective model pages.
prithivMLmods 
posted an update about 1 month ago
view post
Post
3,972
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.

🔗 Space: prithivMLmods/Qwen-Image-2.1-LoRAs-PnP

It supports standard inference, 4-step Turbo inference, custom LoRA lazy repacks, and LoRA Plug and Play (PnP), all in one setting!

🔗 Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras

🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP

To learn more, visit the app page or the respective model pages.
prithivMLmods 
posted an update about 2 months ago
view post
Post
868
VisionGuardrail EVO-2, a multimodal image-classification content-safety model based on Qwen/Qwen3.8-27B, is now available on the Hub!

Stricter image classification than before, with a dense 27-billion-parameter multimodal model, more precise reasoning, and improved captions for classifying visual media.

➠ Models: prithivMLmods/VisionGuardrail-Evo2-27B, prithivMLmods/VisionGuardrail-Evo2-27B-GGUF

➠ Collection: https://huggingface.co/collections/prithivMLmods/visionguardrail-evo2

➠ Previous Models: https://huggingface.co/collections/prithivMLmods/visionguardrail-collection

⤷ To learn more, visit the app page or the respective model pages.
mrfakename 
posted an update about 2 months ago
view post
Post
2,751
We’ve been working with LAION on a voice acting arena. You listen to two models doing the same scene and compare how well they pull it off.

It’s ready to try now - would love to hear what you think 🙂

TTS-AGI/voice-acting-arena
fffiloni 
posted an update about 2 months ago
view post
Post
687
Been pushing Viggle Animate a bit further 👀

Viggle Mine is my take on longer, harder character replacement shots — crowds, distance changes, characters turning their back and reappearing.

Still experimental, but it’s getting surprisingly robust.

Try it : fffiloni/Viggle-Mine 🤗
prithivMLmods 
posted an update about 2 months ago
prithivMLmods 
posted an update 2 months ago
view post
Post
3,898
VisionGuardrail, a multimodal content-safety classifier based on Qwen3.5, is now available on Hugging Face in 4B and 9B variants. It is a direct upgrade to ImageShield-MMCF, providing improved parental controls through conservative visual content-safety filtering.

More About:
➠ hf.co/blog — https://huggingface.co/blog/prithivMLmods/vision-guardrail-mini-blog

➠ Models:
✦ VisionGuardrail-4B: prithivMLmods/VisionGuardrail-4B
✦ VisionGuardrail-9B: prithivMLmods/VisionGuardrail-9B

➠ Dataset:
✦ ImageShield-Guardrail-Pro: prithivMLmods/ImageShield-Guardrail-Pro

⤷ To learn more, visit the app page or the respective model pages.
prithivMLmods 
posted an update 2 months ago
view post
Post
3,120
ImageShield-MMCF — Multimodal Content Filter is a multimodal content-safety classifier built on top of Qwen3.5 and is now available on Hugging Face!

This is the preview initial version (v1.0) of the model, designed to classify visual content as Safe or Unsafe, with a particular focus on detecting Not Safe for Work (NSFW) and other potentially sensitive visual content.

The demo is implemented in the prithivMLmods/opencaption-4b-vl-sft Space, which serves as an active content-safety layer for computer vision tasks. It helps block Not Safe for Work (NSFW) content generation and paves the way for more meaningful and responsible creativity.

⊹ ImageShield-MMCF-0.8B: prithivMLmods/ImageShield-MMCF-0.8B
⊹ ImageShield-MMCF-2B: prithivMLmods/ImageShield-MMCF-2B
  • 2 replies
·
fffiloni 
posted an update 2 months ago
view post
Post
2,221
If an agent can build the obvious demo, the obvious demo probably isn’t worth building anymore.
For years, turning a research repo into something people could actually try was valuable by itself.
That part is becoming automated — and that’s a good thing.

Which means the interesting work moves elsewhere: finding the weird use case, the right interaction, the unexpected model combination — or simply knowing which paper is worth anyone’s attention.

The demo used to be the product. Now it needs a point of view.
  • 1 reply
·
tomaarsen 
posted an update 3 months ago
view post
Post
4,593
🚨 I've just published Sentence Transformers v6.0, introducing MultiVectorEncoder: ColBERT-style late interaction models are now a fourth model type, for training, inference, and interpretation, alongside the dense, sparse, and reranker models! Details:

Where a regular embedding model compresses a whole text into one vector, a multi-vector model keeps one vector per token and scores query against document with the MaxSim operator. That preserves token-level matching information that a single vector has to average away. It is also the state of the art for visual document retrieval, where a text query is matched against page images directly, charts and tables included, with no OCR step in between.

Any PyLate, Stanford ColBERT, or ColPali checkpoint loads straight into the same familiar API: model.encode_query(), model.encode_document(), and model.similarity() just work, whether the documents are texts or page images.

Does it help? LightOn trained LateOn (multi-vector) and DenseOn (dense) on the same data with the same 149M ModernBERT backbone, and the multi-vector model wins on 9 of the 13 NanoBEIR datasets: 0.6868 vs 0.6764 mean NDCG@10. The price is a bigger index, and the new HierarchicalTokenPooling module halves it at roughly no retrieval cost.

Antoine Chaffin, Raphaël Sourty, and I wrote a blog post walking through multi-vector models in practice: loading the various checkpoint formats, encoding and scoring, plugging them into a search stack, running them on page images, and keeping the index affordable. Check it out if you want to get started, or just point your Agent to the URL: https://huggingface.co/blog/multi-vector-encoder

pip install sentence-transformers==6.0.0

Release notes: https://github.com/huggingface/sentence-transformers/releases/tag/v6.0.0
prithivMLmods 
posted an update 3 months ago
view post
Post
5,300
The Qwen3.8 27B demo for object grounding is now available on Hugging Face Spaces.

It features three tasks: Object Detection (Bounding Boxes), Point Localization (Keypoints), and Spatial Guidance (Path Mapping).

Try it now: prithivMLmods/Qwen3.8-27B-Object-Detection
BramVanroy 
posted an update 3 months ago
view post
Post
2,873
**I benchmarked HF buckets against https access for Common Crawl.**

Took me a while to get round to do this but I benchmarked access to Common Crawl via https vs hf buckets. Both experiments were run at night in Europe. I do not think other hardware problems were impacting the speeds since CPU processing time of the non-download pipeline components were highly similar (within 2% identical) and below only the WarcReader speeds of datatrove are used.

Experiment: selected 5 disjoint samples of 64 files each (randomly from the latest crawl; 20,499 docs/file). Those five batches were then processed by 32 single-core tasks with 4GB/core (five batches to calculate CIs). Paired experiment between using https and hf bucket.

- https: 40.0 [39.3-40.6] (seconds per WARC file)
- hf bucket: 172.0 [122.7-221.2]

That is a difference of about 4x in streaming speed. You'll see that https is also more stable (smaller CI).

I also ran raw throughput tests to the endpoints to measure rate limiting (64MiB transfer at 8/32/128/256 concurrent readers) and rate limiting seems not an issue for either: at any of those parallel reader numbers, their respective speeds stay about the same.

Note that, given CC scale, this is still a small test. Rate limiting may become more obvious when processing a full crawl. I do not know whether the https endpoint vs HF bucket will shut you out earlier with which limits.
prithivMLmods 
posted an update 3 months ago
view post
Post
5,584
Made a demo for Text/Image-to-3D Video and Image-to-3D Video asset generation using TRELLIS.2. It is paired with Z-Image-Turbo to accelerate the input image preprocessing pipeline, streamlining the Image-to-3D workflow. The generated GLB (GL Transmission Format) files are converted into MP4 (MPEG-4) videos, making them easy to preview and share. Try it now on Hugging Face Spaces.🤗

➠ Image-to-3D-Video-Asset-Generator: prithivMLmods/Image-to-3D-Video-Asset-Generator
➠ collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
➠ github: https://github.com/PRITHIVSAKTHIUR/Image-to-3D-Video-Asset-Generator

⤷ To learn more, visit the app page or the respective model pages.
fffiloni 
posted an update 4 months ago