Hugging Face's logo

Data Is Better Together Contributor
community
Activity Feed

AI & ML interests

None defined yet.

Recent Activity

Goekdeniz-Guelmez  authored a paper 11 days ago
Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models
SivilTaram  authored a paper about 2 months ago
Diffusion Language Models are Super Data Learners
ljvmiranda921  authored a paper 2 months ago
FilBench: Can LLMs Understand and Generate Filipino?
View all activity

prithivMLmods 
posted an update about 21 hours ago
view post
Post
390
Dropping Image Edit (Object Manipulator): Add or remove specified objects/designs, with flexible support for both single-image and multi-image modes.

🤗 Demo: prithivMLmods/Qwen-Image-Edit-Object-Manipulator

Qwen-Image-Edit-2511-Object-Remover is an adapter (LoRA) developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model. It is specifically designed for precise object removal from images.

⭐ Model: prithivMLmods/Qwen-Image-Edit-2511-Object-Remover

Qwen-Image-Edit-2511-Object-Adder is an adapter (LoRA) developed for Qwen’s Qwen-Image-Edit-2511 image-to-image model. It is specifically designed for precise object addition to images.

⭐ Model: prithivMLmods/Qwen-Image-Edit-2511-Object-Adder

🕹️ Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-object-manipulator
🕹️ github: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-Object-Manipulator

To learn more, visit the app page or the respective model pages.
Sri-Vigneshwar-DJ 
posted an update 1 day ago
view post
Post
112
Domain-specific reasoning is crucial when working with big-budget campaigns on Meta. That's why we've launched an experimental Chain-of-Thought (CoT) reasoning model for critical thinking, tailored to Meta's Andromeda algorithm-based campaign structuring and optimization.

Sri-Vigneshwar-DJ/hawky-ai-h1-mini-1b-experimental
Sri-Vigneshwar-DJ 
posted an update 3 days ago
view post
Post
2847
The recent update to Meta's ad algorithm is very difficult to crack, and even the latest models struggle to keep up with it. To address this, we've created a small experimental dataset for fine-tuning models to better tackle Meta's Andromeda algorithm: Sri-Vigneshwar-DJ/hawky-ai-andromeda-dataset
Sri-Vigneshwar-DJ 
posted an update 7 days ago
prithivMLmods 
posted an update 8 days ago
view post
Post
4025
Update: TRELLIS.2 (Text to 3D, Image to 3D) Gradio with Rerun Embedded demo with improved visualization of the 3D model previewer is now available on Hugging Face. Generate assets and view them in the 3D viewer, powered and streamlined with Microsoft’s TRELLIS.2 and Tongyi-MAI’s Z-Image-Turbo models.

🤗 TRELLIS.2 (Demo): prithivMLmods/TRELLIS.2-Text-to-3D
🕹️ GitHub: https://github.com/PRITHIVSAKTHIUR/TRELLIS.2-Text-to-3D-RERUN
🕹️ Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations

To know more about it, visit the app page or the respective model page!
prithivMLmods 
posted an update 9 days ago
view post
Post
4134
Introducing the Qwen-Image-Edit-2511-LoRAs-Fast demo, featuring image property comparison and contrast, built on top of Gradio and the combined Rerun SDK. It supports single and multi-image edits with existing LoRAs that are lazily loaded. (Note: This is still an experimental Space for Qwen-Image-Edit-2511.)

⭐ Space Demo: prithivMLmods/Qwen-Image-Edit-2511-LoRAs-Fast
⭐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-2511-LoRAs-Fast-Multi-Image-Rerun
⭐ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

To know more about it, visit the app page or the respective model page!
  • 2 replies
·
Goekdeniz-Guelmez 
authored a paper 11 days ago
prithivMLmods 
posted an update 16 days ago
view post
Post
3668
Introducing demos for new SOTA models from AI2: SAGE-MM (Smart Any-Horizon Agents for Long-Video Reasoning) and Molmo-2, an open vision-language model that supports multi-image (QA and pointing) and video (QA, pointing, and tracking). The respective demo-related collections are listed below. 🎃🔥

✨ SAGE-MM [Video-Reasoning]: prithivMLmods/SAGE-MM-Video-Reasoning
✨ Molmo2 [Demo]: prithivMLmods/Molmo2-HF-Demo

🎃 GitHub[SAGE-MM]: https://github.com/PRITHIVSAKTHIUR/SAGE-MM-Video-Reasoning
🎃 GitHub[Molmo2]: https://github.com/PRITHIVSAKTHIUR/Molmo2-HF-Demo
🎃 Multimodal Implementations: https://huggingface.co/collections/prithivMLmods/multimodal-implementations

To know more about it, visit the app page or the respective model page!
  • 1 reply
·
prithivMLmods 
posted an update 17 days ago
view post
Post
2036
Introducing TRELLIS.2 Text-to-3D. The demo for the TRELLIS.2-4B (Image-to-3D) model is streamlined with the Z-Image Turbo image generation model to enable Text-to-3D functionality. There is no need for input assets, making a small leap forward for ideation. Optionally, it also includes default support for Image-to-3D inference using direct image assets. Find the demo and related collections below... 🤗🔥

✨ TRELLIS.2-Text-to-3D [Demo]: prithivMLmods/TRELLIS.2-Text-to-3D
✨ Multimodal Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
✨ Github: https://github.com/PRITHIVSAKTHIUR/TRELLIS.2-Text-to-3D

To know more about it, visit the app page or the respective model page!
ZennyKenny 
posted an update 19 days ago
view post
Post
1957
🍓 One of the coolest parts about being an early Strawberry user has been the opportunity to build on the app at the ground floor.

The platform already has a ton of great integrations that let you interact with your external apps directly with tools, but I wanted to add the ability to do stuff in Slack as well.

💪 So I took the base Anthropic Slack MCP server, added a whole bunch of new tools, and generalized it as an HTTP-based SSE-server and deployed it in like 2 minutes with Railway so that Strawberry could make use of it (as can Claude or any other MCP client).

Now, you can Chat with your Strawberry Companion (or Claude, or whatever) and do things like:
➡️ Get caught up across all of your Slack channels after a long weekend or noisy incident without having to read 20 threads in 10 different channels
➡️ Create, read, and edit Canvases, Messages, and Channels
➡️ Take any resources or content that you're using in your Chat and inject it directly into Slack without copy / paste

😎 I'm pretty pleased with the results, and I made a short demo video showing the results of the work (link in comments). The best part is, it's available on GitHub for anyone else to use too (link in the comments, instructions in the README). The setup takes about 5-10 minutes.
  • 2 replies
·
prithivMLmods 
posted an update 19 days ago
view post
Post
2004
Demo for Molmo2 on Hugging Face is live now, including Single/Multi-Image VQA, Visual Pointing/Grounding, Video VQA, and Video Point Tracking. Find the demo and related collections below. 🔥🤗

● Molmo2 HF Demo🖥️: prithivMLmods/Molmo2-HF-Demo
● Model Collection: https://huggingface.co/collections/allenai/molmo2
● Related Multimodal Space Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations

To know more about it, visit the app page or the respective model page!
prithivMLmods 
posted an update 20 days ago
view post
Post
5529
Introducing the Z Image Turbo LoRA DLC App, a gallery space for plug-and-play Z-Image-Turbo LoRAs. It features a curated collection of impressive LoRAs for generating high-quality images. By default, it runs on the base model. Simply choose a LoRA, type your prompt, and generate images. You can find the app and more details below. 🤗🧪

● Space [Demo]: prithivMLmods/Z-Image-Turbo-LoRA-DLC
● Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
● Check the list of Z-Image LoRA's: https://huggingface.co/models?other=base_model:adapter:Tongyi-MAI/Z-Image-Turbo
● Github: https://github.com/PRITHIVSAKTHIUR/Z-Image-Turbo-LoRA-DLC

Other related image gen spaces:-

● FLUX-LoRA-DLC2: prithivMLmods/FLUX-LoRA-DLC2
● FLUX-LoRA-DLC: prithivMLmods/FLUX-LoRA-DLC
● Qwen-Image-LoRA-DLC: prithivMLmods/Qwen-Image-LoRA-DLC
● Qwen-Image-Edit-2509-LoRAs-Fast: prithivMLmods/Qwen-Image-Edit-2509-LoRAs-Fast
● Qwen-Image-Edit-2509-LoRAs-Fast-Fusion: prithivMLmods/Qwen-Image-Edit-2509-LoRAs-Fast-Fusion

& more...

To know more about it, visit the app page or the respective model page!
  • 2 replies
·
davidberenstein1957 
posted an update 20 days ago
prithivMLmods 
posted an update 28 days ago
view post
Post
2732
Introducing the D.Markdown Experimental Models, Proxima and Epsilon OCR models, built on top of Qwen3-VL and Qwen2.5-VL respectively. Proxima is optimized for Markdown generation and is capable of embedding inline programming code snippets and generating rich nodes such as HTML, XML, JSON, and YAML. Epsilon is optimized for reconstructing complex layouts including tables, forms, and mathematical content. 🌌✨

● proxima-ocr-d.markdown-post3.0.l: prithivMLmods/proxima-ocr-d.markdown-post3.0.l
● epsilon-ocr-d.markdown-post3.0.m: prithivMLmods/epsilon-ocr-d.markdown-post3.0.m
● proxima-ocr-d.markdown-post3.0.l-gguf: prithivMLmods/proxima-ocr-d.markdown-post3.0.l-GGUF
● epsilon-ocr-d.markdown-post3.0.m-gguf: prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF

● Collection: https://huggingface.co/collections/prithivMLmods/dynamic-markdowns
● Multimodal Apps: https://huggingface.co/collections/prithivMLmods/multimodal-implementations

👉 These models are stage progression models, and currently they may contain artifacts.

To know more about it, visit the app page or the respective model page!
flozi00 
posted an update 28 days ago
view post
Post
285
We have covered Tensor Parallelism for slicing matrices and Pipeline Parallelism for stacking layers. But what if your model isn't just deep or wide—it's a sprawling Mixture-of-Experts (MoE) architecture like Mixtral or DeepSeek, with trillions of parameters that are mostly idle per token?

Replicating those experts wastes VRAM. Slicing them with TP wastes bandwidth. The solution is Expert Parallelism (EP), which distributes the experts themselves across GPUs and routes tokens to wherever their "chosen" expert lives.

The hardware catch? It is not matrix splitting or pipeline bubbles—it's the "Router's Dilemma." You must shuffle massive volumes of tokens across the cluster using All-to-All communication, and any imbalance can leave expensive GPUs idle.

My latest guide dives into the mechanics of EP and why the interconnect becomes the ultimate bottleneck.

In this breakdown, we explore:

The Token Routing Lifecycle
A four-step hardware flow: Local routing to pick experts, Dispatch (All-to-All shuffle), Expert computation on the "home" GPU, and Combine (another All-to-All to return results).

The All-to-All Primitive
Unlike the ring-based syncs in TP, All-to-All creates a dense mesh of personalized data transfers. We compare it to All-Reduce and show why uneven token distribution (load imbalance) causes network congestion and compute skew.

Load Balancing: The Hardware Nightmare
If one expert gets 90% of the tokens, its GPU bottlenecks while others stall. We discuss mitigation strategies like token dropping and auxiliary losses to keep utilization high.

The article includes a raw PyTorch implementation of an EP layer using torch.distributed.all_to_all_single to reveal exactly how the data shuffles and where the stalls happen.

Read the full hardware-centric guide here:
https://flozi.net/en/guides/ai/scaling/expert_parallel
  • 1 reply
·
prithivMLmods 
posted an update 29 days ago
view post
Post
1130
Try CUA GUI Operator 🖥️ Space, the demo of some interesting multimodal ultra-compact Computer Use Agent (CUA) models in a single app, including Fara-7B, UI-TARS-1.5-7B, and Holo models, to perform GUI localization tasks.

● CUA-GUI-Operator [Demo]: prithivMLmods/CUA-GUI-Operator
● Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations

Other related multimodal spaces

● Qwen3-VL: prithivMLmods/Qwen3-VL-HF-Demo
● Multimodal-VLM-v1.0: prithivMLmods/Multimodal-VLM-v1.0
● Vision-to-VibeVoice-en: prithivMLmods/Vision-to-VibeVoice-en

I have planned to add Chrome sandboxes to streamline it and turn it into a browser based CUA multimodal tool, which will be added to the same space soon.

To know more about it, visit the app page or the respective model page!
  • 1 reply
·
ZennyKenny 
posted an update about 1 month ago
view post
Post
215
What a trip. Just walked through @burtenshaw and @evalstate tutorial on adding Hugging Face Skills to your Claude Code agent so you can fine tune LLMs by chatting with AI.

These are the kinds of innovations that are going to help everyone benefit from the power of Artificial Intelligence. Well done gentlemen and thank you for sharing.
  • 1 reply
·
prithivMLmods 
posted an update about 1 month ago
view post
Post
3566
One speech model with seven voices, streamlined with multimodal capabilities for vision tasks. Performs vision(image-text) to audio inference with Qwen2.5-VL + VibeVoice-Realtime-0.5B. Vision to VibeVoice (EN) - The demo is live. 🗣️🔥

🤗 Vision-to-VibeVoice-en [Demo]: prithivMLmods/Vision-to-VibeVoice-en
✨ Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
✨ Speech [VibeVoice-Realtime-0.5B]: microsoft/VibeVoice-Realtime-0.5B
✨ Vision [Qwen2.5-VL]: Qwen/Qwen2.5-VL-7B-Instruct

To know more about it, visit the app page or the respective model page!
·
prithivMLmods 
posted an update about 1 month ago
view post
Post
3714
Hello everyone,

The
strangerzonehf [HF] Community / Organization Page, which is maintained by me, has reached the Top 10 Developer Pages ranking at 6th place, contributing 3.4% in the calendar cycle from August 2024 to August 2025. It is also the only South Asia / Indian page in the list. I could not be more proud to be doing things for the community. ❤️🤗

Source: https://www.dataprovenance.org/economies-of-open-intelligence.pdf

It is a pleasure to be a part of it.
Thank you!
@prithivMLmods
flozi00 
posted an update about 1 month ago
view post
Post
3115
We recently discussed how Tensor Parallelism slices matrices to reduce latency within a single node. But what happens when you need to scale beyond that, where the bandwidth drops?

That is where Pipeline Parallelism (PP) takes over.

Instead of slicing the operation, PP slices the model depth. It turns your GPU cluster into an assembly line: GPU 0 handles layers 1-12, GPU 1 handles 13-24, and so on.

The hardware challenge here isn't the interconnect speed—it is the "Pipeline Bubble." In a naive setup, expensive H100s sit idle for most of the cycle waiting for data to flow through the chain.

My latest guide breaks down the scheduling strategies used to minimize this idle silicon time.

In this deep dive, we cover:

The Hardware Mechanics: Vertical Slicing
Unlike TP which requires "chatty" All-Reduce operations, PP relies on lightweight Point-to-Point (Send/Recv) communication. This makes it the only viable strategy for crossing node boundaries over Ethernet or InfiniBand.

Fighting the Bubble: 1F1B vs. GPipe
We analyze the scheduling algorithms that keep the GPUs fed:

GPipe: The "flush and fill" approach. Simple, but memory-intensive.
1F1B (One-Forward-One-Backward): The industry standard. By interleaving forward and backward passes, we aggressively free up memory and reduce the bubble size.
The Math of Efficiency
The "Bubble" is a mathematical inevitability. We look at the efficiency formula
M+N−1
M
​
to understand why you need massive global batch sizes to make PP worth the effort.

The article includes a conceptual PyTorch implementation of the 1F1B state machine to illustrate exactly how the data is handed off between stages.

Read the full breakdown here:
https://flozi.net/en/guides/ai/scaling/pipeline_parallel