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

AI & ML interests

A Family of Dynamic UltraFast Small Language Models Ready for Embodied Artificial General Intelligence!

Recent Activity
emanuelaborosย  authored a paper 6 days ago
Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity Linking
emanuelaborosย  authored a paper 6 days ago
When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations
JingzeShiย  authored a paper 11 days ago
MassAlloc Attention: Let Attention Allocate Its Own Compute
View all activity
prithivMLmodsย 
posted an update 5 days ago
view post
Post
3457
OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!

๐Ÿค— 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.

๐Ÿ“ฆ Models: 27B, 9B, 4B โ€” prithivMLmods/OneDecision-VisionGuard-27B-SFT, prithivMLmods/OneDecision-VisionGuard-9B-SFT, prithivMLmods/OneDecision-VisionGuard-4B-SFT

โ†—๏ธ Collection: https://huggingface.co/collections/prithivMLmods/onedecision-visionguard

To learn more, visit the app page or the respective model pages.
emanuelaborosย 
authored 2 papers 6 days ago
JingzeShiย 
authored 2 papers 11 days ago
emanuelaborosย 
authored 2 papers 12 days ago
JingzeShiย 
posted an update 13 days ago
view post
Post
101
Sharing two recent explorations in attention design from our team.

We started with two straightforward questions: Does every attention head need to repeatedly attend to the entire causal history? Once attention scores have been computed, do regions with very little contribution still need the full subsequent computation?

We explored two approaches:

CoWindow Attention (CoWA): Let heads share the work of accessing history. Heads share local context and divide distant context into complementary windows. Each head attends sparsely, while the heads collectively cover the full causal history.
CoWindow Attention: Full Causal Coverage Is a Collective Property (2609.32704)

MassAlloc Attention (MALA): Let attention allocate its own compute. MALA preserves full causal QK scoring, then uses attentionโ€™s own softmax statistics to reduce subsequent computation in low-contribution regions.
MassAlloc Attention: Let Attention Allocate Its Own Compute (2609.32712)

Both approaches support training forward and backward passes, as well as inference prefill and decoding. In attention-operator benchmarks at 128K tokens on 8ร—H100 with TP=8, compared with FullAttn:

CoWA: 7.4ร— forward, 8.6ร— backward, and 3.0ร— decoding speedups.
MALA: 2.2ร— forward, 3.0ร— backward, and 1.6ร— decoding speedups.

We also conducted scaling experiments from 0.6B to 14B, alongside separate continued-training experiments at 32B. During 14B training with 32K context, CoWA and MALA reduced total training FLOPs by 28.5% and 23.1%, respectively, while maintaining performance comparable to FullAttn on the evaluated model capabilities.

From method design to kernel implementation to model training, our goal was to explore which attention computations can be eliminated, and how to turn those savings into practical gains in ML infrastructure.
JingzeShiย 
submitted 2 papers to Daily Papers 13 days ago
arudradeyย 
posted an update 15 days ago
prithivMLmodsย 
posted an update 18 days ago
view post
Post
3914
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.

๐Ÿ”— 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!

๐Ÿ”— Qwen-Image-2.1 Image-to-Image LoRAs: https://huggingface.co/collections/prithivMLmods/qwen-image-21-image-to-image-loras

๐Ÿ”— GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-2.1-LoRAs-PnP

To learn more, visit the app page or the respective model pages.
GGUFGuyย 
posted an update 20 days ago
view post
Post
171
๐Ÿš€ **Introducing NoviAIBot!**

NoviAIBot is the official automation bot for **Novi AI** on Hugging Face.

It can interact with Hugging Face discussions and pull requests, search the web, run Python code, work with Posts, follow organizations, and assist with model training and publishing.

๐Ÿง  Powered by **NVIDIA Nemotron 3 Super** through Ollama Cloud, with each discussion maintaining its own recent conversation context.

NoviAIBot is built to make working with Novi AI and Hugging Face more interactive and automated.

**The bot is now live.** ๐Ÿค–

โ†’ @NoviAIBot
  • 44 replies
ยท
prithivMLmodsย 
posted an update 26 days ago
view post
Post
845
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.

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

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

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

โคท To learn more, visit the app page or the respective model pages.
prithivMLmodsย 
posted an update 29 days ago
view post
Post
492
Scribble-Board-Fast is a sketch-to-image workspace powered by Klein-9B, transforming doodles, brush strokes, stickers, and uploaded images into high-fidelity visuals with 4-step distilled sampling.

> Space: prithivMLmods/Scribble-Board-Fast
> GitHub: https://github.com/PRITHIVSAKTHIUR/Scribble-Board-Fast

> To learn more, visit the app page or the respective model pages.
GGUFGuyย 
posted an update about 1 month ago
view post
Post
5386
wait why can i post
  • 24 replies
ยท
prithivMLmodsย 
posted an update about 1 month ago
view post
Post
3872
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:
โž  hf.co/blog โ€” https://huggingface.co/blog/prithivMLmods/vision-guardrail-mini-blog

โž  Models:
โœฆ VisionGuardrail-4B: prithivMLmods/VisionGuardrail-4B
โœฆ VisionGuardrail-9B: prithivMLmods/VisionGuardrail-9B

โž  Dataset:
โœฆ ImageShield-Guardrail-Pro: prithivMLmods/ImageShield-Guardrail-Pro

โคท To learn more, visit the app page or the respective model pages.
prithivMLmodsย 
posted an update about 2 months ago
view post
Post
3109
ImageShield-MMCF โ€” 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.

โŠน ImageShield-MMCF-0.8B: prithivMLmods/ImageShield-MMCF-0.8B
โŠน ImageShield-MMCF-2B: prithivMLmods/ImageShield-MMCF-2B
  • 2 replies
ยท
Evanwu50020ย 
in SmallDoge/niah about 2 months ago

[bot] Conversion to Parquet
#1 opened 7 months ago by
parquet-converter
prithivMLmodsย 
posted an update about 2 months ago
view post
Post
5295
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