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

AI & ML interests

None defined yet.
prithivMLmodsΒ 
posted an update 4 days ago
view post
Post
560
Flux-3-Image-Klein-LoRAs-Fast is now live on Hugging Face Spaces.πŸ€—πŸ”₯

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!

πŸ”— Space: prithivMLmods/flux-3-image-klein-loras-fast

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

πŸ”— GitHub: https://github.com/PRITHIVSAKTHIUR/flux-3-image-klein-loras-fast

To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update 22 days ago
view post
Post
4,753
OneDecision-VisionGuard-Demo is now available on Hugging Face Spaces!

πŸ€— 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.

πŸ“¦ Models: 27B, 9B, 4B β€” 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.
arudradeyΒ 
posted an update about 1 month ago
prithivMLmodsΒ 
posted an update about 1 month ago
view post
Post
3,955
Qwen-Image-2.1 Plug and Play LoRA App is now live on Hugging Face Spaces.

πŸ”— 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!

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

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

To learn more, visit the app page or the respective model pages.
medmekkΒ 
posted an update about 1 month ago
view post
Post
4,392
πŸš€ Introducing Halo 1.0

Today, we are open-sourcing Halo, the training framework we use to train every model at White Circle.

It comes with:
🧠 Full post-training stack: SFT, DPO/KTO/SMPO, reward modeling, GRPO, distillation
πŸ€– Async multi-turn RL with vLLM/SGLang rollouts and sandboxed tool use
⚑ ~2.8Γ— TRL throughput on 8Γ— B300 (EP+FSDPv2, FA4, fp8/fp4)
πŸ€— Dense HF models + 15 MoE families (Qwen, GLM, Mistral, DeepSeek-V4…)
πŸ› οΈ One halo command, prebuilt Docker images, and docs for humans and agents

πŸ’» https://github.com/whitecircle/halo

Try it and tell us what you're training
  • 1 reply
Β·
prithivMLmodsΒ 
posted an update about 1 month ago
view post
Post
863
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

β€· To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update about 2 months ago
view post
Post
504
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.
mahwizzzzΒ 
posted an update about 2 months ago
view post
Post
261
I implemented the attention-free bidirectional encoder architecture Avey-B for Urdu a compact 24.87M-parameter language encoder built for efficient Urdu NLP research.

Original Avey-B paper: Avey-B (2602.15814)
Urdu model: mahwizzzz/avey-b-ur
prithivMLmodsΒ 
posted an update about 2 months ago
view post
Post
3,891
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 β€” 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

β€· To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update 2 months ago
view post
Post
3,117
ImageShield-MMCF β€” 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
Β·
prithivMLmodsΒ 
posted an update 2 months ago
view post
Post
5,298
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
mahwizzzzΒ 
posted an update 3 months ago
prithivMLmodsΒ 
posted an update 3 months ago
view post
Post
5,580
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.πŸ€—

➠ 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

β€· To learn more, visit the app page or the respective model pages.
badaouiΒ 
posted an update 3 months ago
view post
Post
2,504
432 GB of ultra-fast HBM4 and up to 23.3 TB/s of memory bandwidth on a single GPU 🀯.

Two weeks ago, we got early access to AMD's new Instinct MI455X, and our first goal was simple: make sure πŸ€— Transformers works on day one.

Over the past few weeks, we worked closely with the AMD team to validate the platform, enable Flash Attention, add torchcodec support for multimodal models, and resolve issues uncovered during testing.

The result:
βœ… 99.5% success rate across our 24 core Transformers model architectures - already on par with our daily CI on previous AMD and NVIDIA platforms.

The hardware is just as exciting. With 432 GB of HBM per GPU, our early capacity experiments showed more than 3Γ— the concurrent long-context requests compared to MI300, thanks to the much larger KV cache capacity.

A huge thanks to the AMD team for the early access and the great collaboration!

Read the full blog πŸ‘‡
https://huggingface.co/blog/badaoui/transformers-on-amd-mi455
  • 1 reply
Β·
codelionΒ 
authored 4 papers 3 months ago
mmhamdyΒ 
posted an update 4 months ago
view post
Post
248
Decades before the modern scaling laws, this paper showed that neural networks behavior under scale follows remarkably predictable laws.

In 1993, researchers at Bell Labs were grappling with a constraint that feels entirely familiar (and contemporary): datasets were outgrowing the available hardware, and training a model to the end was becoming too expensive. To evaluate an architectural tweak to a state-of-the-art model (at the time it was LeNet) on 60,000 samples meant burning up to three weeks of compute time.

To save compute, people would train candidate architectures on small subsets of the data, assuming that the top performer at small scale would remain the top performer at full scale. But with our future wisdom, we know this is not the case.

In "Learning Curves: Asymptotic Values and Rate of Convergence (NeurIPS 93)", using insights from statistical mechanics, they proposed a practical and principled method for predicting the performance of classifiers trained on large datasets (at the time, models were assumed to be large enough). The method was based on a simple power-law modeling of the expected training and test errors.

It is often noted that many of today's breakthroughs in AI and deep learning are actually decades-old concepts that simply lacked the computational power to be tested at the time. While there is some truth to that, it highlights a more valuable lesson: there is immense worth in revisiting early literature and reflecting on foundational ideas we may have prematurely left behind.

So, go explore and find your own inspiration. The current trend has enough champions already!
  • 2 replies
Β·
codelionΒ 
posted an update 4 months ago
view post
Post
828
SPROG-9M β€” a 9.37M parameter model trained from scratch to solve GSM8K-style math without using an LLM at inference.

The model, codelion/sprog-9m, predicts symbolic programs over number slots, then a deterministic executor does the arithmetic. With a simple verifier, it reaches ~11.8% on GSM8K test.

We also released the dataset: codelion/gsm8k-synth, 117K validated synthetic GSM8K-style problems.

Tiny model, no pretraining, no LLM at inference, runs on a laptop.