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
QJerryΒ  authored a paper 12 days ago
D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
QJerryΒ  authored a paper 12 days ago
High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation
oooranzΒ  authored a paper about 1 month ago
Active Tabular Augmentation via Policy-Guided Diffusion Inpainting
View all activity
ShrijanagainΒ 
posted an update 1 day ago
view post
Post
57
Welcome Researcher and Developers!

SKT AI Labs, we are pushing the boundaries of AI architecture and researchβ€”and today, we are thrilled to open our doors to the global research community!

​We warmly welcome researchers, developers, and AI enthusiasts to join us and contribute to our R&D efforts.

​πŸ§ͺ What You Can Explore:

We invite you to experiment with our WMF (Weight Manifold Fusion) technology. You can test this high-dimensional fusion technique on smaller models to gain a deeper understanding of its behavior and token convergence.

---------- CHECK OUT:

SPACE : SKT-NRS/RD
EXPERIMENT : sKT-Ai-Labs/SKT-SURYA-H
DIRECT TO MAIN DISCUSSION : SKT-NRS/RD#1

β€‹πŸ€ Your Feedback Shapes the Future :

​If it works: Fantastic! Share your results with us and contribute directly to the core vision of SKT AI Labs.

​If it doesn't work: No problem at all! Your critical feedback is just as valuable to us. Every experiment and anomaly helps us refine this architecture to make it more stable and robust.

​We firmly believe that true innovation stems from community collaboration and transparent testing. Let's build the future of advanced AI together. Your ideas, test results, and feedback are always welcome!

You Can Still Research and Development On WMF Only SKT-SURYA-H Model is Dismissed.

​Let's innovate and build together! πŸ’‘
ShrijanagainΒ 
posted an update 4 days ago
view post
Post
150
πŸš€ Big News for the AI Community! πŸ”₯

We’re excited to release NRS_QWEN_MYTHOS_1M β€” a powerful reasoning model built on Qwen 3.5 9B!
At SKT AI LABS, we’ve supercharged this 9B model with our proprietary Neural Reasoning System (NRS) to deliver next-level performance.

πŸ”₯ Why This Model is a Game-Changer:
βœ… 100x Reasoning Capacity β€” Exceptional deep logical thinking and complex problem-solving
βœ… 1 Million Token Context β€” Perfect for massive codebases, long documents, and multi-turn agentic workflows
βœ… Advanced Thinking Mode β€” Native <think> tags for true step-by-step Chain-of-Thought reasoning
βœ… Tool-Use Ready β€” Optimized for Python execution, Web Search, and self-correction
βœ… Blazing Fast β€” Runs smoothly on consumer GPUs like RTX 3090/4090

Technical Highlights:

Base: Qwen 3.5 9B
Tuning: NRS-specific high-quality reasoning data
Context: 1M Tokens (YaRN Scaling)
License: NRS DOCS

Whether you’re a developer building coding agents, a researcher working with long-context data, or someone who loves powerful reasoning β€” this model is built for you.

πŸ‘‰ Try it now on Hugging Face:
SKT-NRS/NRS_QWEN_MYTHOS_1M

Drop a comment: What will you build with it first? πŸ‘‡
#AI #OpenSource #LLM #Qwen #ReasoningModel #HuggingFace #NewModel #AICommunity
eienmojikiΒ 
posted an update 6 days ago
QJerryΒ 
authored 2 papers 12 days ago
KingNishΒ 
posted an update 15 days ago
view post
Post
4338
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos

Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.

Trained on: H100s from Modal

The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.

Everything is open:
πŸ€– Demo β†’ build-small-hackathon/OpenMythos
🧠 Model β†’ build-small-hackathon/OpenMythos
πŸ“¦ CVE Dataset β†’ build-small-hackathon/CVE_Vulnerailities_Detailed
πŸ“„ ArXiv Dataset β†’ himanshu17HF/ArvixImport-Filtered-Final

Try it out and let us know where it breaks πŸ™
  • 2 replies
Β·
AbhaykoulΒ 
posted an update 15 days ago
view post
Post
230
Shipped v0.1.2 of vtx β€” a minimalist coding agent for the terminal.

Most agentic CLIs ship 10k+ token system prompts. Vtx is ~2,200. Less prompt overhead means more room for your code in the model's context window.

Vtx is a from-scratch Python implementation of the design philosophy behind pi-mono β€” same principles, pure Python, no transpiled runtime.

What ships out of the box:

β†’ Textual TUI + headless CLI (vtx -p "fix the failing test")
β†’ 49 LLM provider gateways, all declared in a single provider.yaml
β†’ 5 core tools (read / edit / write / bash / find) plus web search and fetch
β†’ Session tree with compaction, handoff, and resume
β†’ AGENTS.md / CLAUDE.md auto-discovery
β†’ Skills system β€” drop SKILL.md files in .agents/skills/ and they become slash commands
β†’ Two OAuth flows (GitHub Copilot device flow, OpenAI Codex PKCE)
β†’ Two-mode permissions: prompt (default) or auto, with a safe-command allowlist

This release adds a proper extension system. Register new LLM-callable tools, intercept tool calls, hook lifecycle events, and add slash commands from a single register(api) function in a Python file under ~/.vtx/agent/extensions/. Extensions can override built-in tools by name and chain handler logic across subscribers.

Apache 2.0. uv tool install vtx-coding-agent and you're running.

GitHub: https://github.com/OEvortex/vtx-coding-agent
PyPI: https://pypi.org/project/vtx-coding-agent

Built in the open. Feedback, extensions, and PRs welcome.
prithivMLmodsΒ 
posted an update 16 days ago
view post
Post
4697
Wan2.2-I2V-Fast with highly upscaled sequential frame sampling is now available as a Spaces demo, built using Wan2.2-I2V and FLUX.2-Klein. Try the demo using the links below.πŸ‘‡

➠ wan2.2-i2v-fast : prithivMLmods/wan2.2-i2v-fast
➠ github: https://github.com/prithivsakthiur/wan2.2-i2v-fast
➠ collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

β€· To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update about 1 month ago
prithivMLmodsΒ 
posted an update about 1 month ago
view post
Post
6209
PiD β€” Pixel Diffusion Decoder Image Edit Upscale and Image Generation Upscale, an all-in-one demo, is now live on Spaces! Great improvements in realism-based image generation and editing are powered by FLUX.2-Klein, while image generation is paired with Z-Image, and upscaling is enabled by default!

πŸ€— Space: prithivMLmods/PiD-Image-Upscaler
πŸ”— Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

πŸ€— > To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update about 1 month ago
view post
Post
5599
I've made 8 Spaces in the Qwen-Image-Edit series, and out of them, 5 Spaces reached β€œSpace of the Week”! A few Spaces are still topping the list even after many months.

Cumulatively, the series has crossed 8.2 million+ ZeroGPU runs and nearly 4 million visitors overall.

Thanks for all the community support! πŸ€—β€οΈ

πŸ”— Spaces: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
  • 4 replies
Β·
ShrijanagainΒ 
posted an update about 1 month ago
view post
Post
2615
We are pleased to announce that the W-IMG Vision Dataset infrastructure is officially live.

The complete asset infrastructure is now accessible on Hugging Face for internal validation and architecture scaling targets.

Dataset Endpoint - sKT-Ai-Labs/W-IMG

#SovereignAI #ComputerVision #MachineLearning #OpenSource
oooranzΒ 
authored a paper about 1 month ago
Ksgk-fyΒ 
authored a paper about 1 month ago
Ksgk-fyΒ 
submitted a paper to Daily Papers about 2 months ago
oooranzΒ 
submitted a paper to Daily Papers about 2 months ago
prithivMLmodsΒ 
posted an update 2 months ago
view post
Post
5948
Multimodal-Edge Demo, a node-based inference canvas demo, is now live on Spaces. It features node-based Transformers for fast inference across 10+ edge-device multimodal models on the Hub, all within a single space. The series includes models from Qwen3.5, Qwen3-VL, Gemma 4, and the LFM 2.5 VL model series, with support for reasoning and grounding tasks.

πŸ€— Demo: prithivMLmods/Multimodal-Edge-Node
πŸ”— GitHub: https://github.com/PRITHIVSAKTHIUR/Multimodal-Edge-Node
βœ… Multimodal Apps Collections: https://huggingface.co/collections/prithivMLmods/hall-of-multimodal-apps

πŸ€— > To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update 2 months ago
view post
Post
1935
Now, a collection of various compression schemes for Qwen3.6 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. πŸ‘‡

πŸ”— Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions
πŸ”— Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions

πŸ€— > To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update 2 months ago
view post
Post
4231
HY-World-2.0 β€” A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds is now available on Spaces, and it works both as native Gradio components and in Gradio server mode.

> HY-World-2.0-Demo: prithivMLmods/HY-World-2.0-Demo
> HY-World-2.0 [Server Mode]: prithivMLmods/HY-World-2.0-Demo
> Featuring 3D reconstruction and Gaussian splats with the Rerun viewer, along with camera poses, depth maps, and surface normals.
> In Server Mode, Gradio is served via FastAPI, with FastAPI remaining the top-level server.
> Model: tencent/HY-World-2.0
> GitHub: https://github.com/PRITHIVSAKTHIUR/HY-World-2.0-Demo

πŸ€—To learn more, visit the app page or the respective model pages.
prithivMLmodsΒ 
posted an update 3 months ago
view post
Post
6252
A new comparator on Spaces showcases Standard FLUX.2 Decoder vs. FLUX.2 Small Decoder. The Small Decoder is ~1.4Γ— faster, uses ~1.4Γ— less VRAM, and maintains near-identical image quality. It has ~28M parameters with narrower channels [96, 192, 384, 384] vs. [128, 256, 512, 512], and the demo supports sequence generation by running both decoders simultaneously and comparing the results side by side.

πŸ€— Comparator: https://huggingface.co/spaces/prithivMLmods/Flux.2-4B-Decoder-Comparator
πŸ”— FLUX.2-small-decoder: black-forest-labs/FLUX.2-small-decoder
πŸ”— GitHub: https://github.com/PRITHIVSAKTHIUR/Flux.2-4B-Encoder-Comparator
🚁 Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection

πŸ€— > App built on the Gradio SDK. To learn more, visit the app page or the respective model pages.