Prithiv Sakthi's picture

Building on HF

Prithiv Sakthi PRO

prithivMLmods

hugging-science

·

https://linktr.ee/prithivsakthi

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow🤗

Recent Activity

reacted to theirpost with 🚀 about 1 hour ago

Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. 👇 🔗 Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions 🔗 Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions 🤗 > To learn more, visit the app page or the respective model pages.

reacted to theirpost with ❤️ about 1 hour ago

Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. 👇 🔗 Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions 🔗 Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions 🤗 > To learn more, visit the app page or the respective model pages.

reacted to theirpost with 👍 about 1 hour ago

Now, a collection of various compression schemes for Gemma 4 and the abliterated version 1 of dense models is available on the Hub. Check it out via the links below. 👇 🔗 Qwen3.6-MoE: https://huggingface.co/collections/prithivMLmods/qwen36-35b-a3b-compressions 🔗 Qwen3.6-27B Compressions: https://huggingface.co/collections/prithivMLmods/qwen36-27b-compressions 🤗 > To learn more, visit the app page or the respective model pages.

View all activity

Organizations

upvoted a collection about 19 hours ago

Qwen3.6-27B Compressions

Collection of various compressed versions of the Qwen3.6-27B native multimodal model. • 4 items • Updated about 5 hours ago • 1

upvoted a collection 1 day ago

WildDet3D

This is the collection of WildDet3D artifacts, including demos, model checkpoints and data. https://github.com/allenai/WildDet3D • 8 items • Updated 10 days ago • 17

upvoted an article 2 days ago

Article

Building a Fast Multilingual OCR Model with Synthetic Data

6 days ago

•

28

upvoted 2 papers 4 days ago

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs

Paper • 2604.13226 • Published 9 days ago • 10

HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System

Paper • 2604.14125 • Published 8 days ago • 19

upvoted a changelog 4 days ago

Hugging Face Changelog

Spaces agents.md for your coding agents

6 days ago

• 100

upvoted a collection 5 days ago

Qwen3.6-35B-A3B Compressions

Collection of various compressed versions of the Qwen3.6-35B-A3B native multimodal model. • 4 items • Updated 4 days ago • 1

upvoted 3 papers 5 days ago

GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens

Paper • 2604.15284 • Published 7 days ago • 24

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 8 days ago • 108

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework

Paper • 2604.15308 • Published 7 days ago • 27

upvoted a changelog 7 days ago

Hugging Face Changelog

Introducing Kernels

8 days ago

• 143

upvoted an article 9 days ago

Article

Stop benchmarking inference providers

9 days ago

•

8

upvoted 2 papers 10 days ago

WildDet3D: Scaling Promptable 3D Detection in the Wild

Paper • 2604.08626 • Published 14 days ago • 240

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published 14 days ago • 66

upvoted 2 papers 11 days ago

MolmoWeb: Open Visual Web Agent and Open Data for the Open Web

Paper • 2604.08516 • Published 14 days ago • 42

HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents

Paper • 2604.07430 • Published 15 days ago • 185

upvoted a changelog 13 days ago

Hugging Face Changelog

ZeroGPU overquota

13 days ago

• 126

upvoted an article 14 days ago

Article

Safetensors is Joining the PyTorch Foundation

15 days ago

•

32

upvoted 2 collections 14 days ago

Gemma 4 Uncensored [MAX] + Compression(s) - [`β ]

Collection of Uncensored Variants of Gemma 4 Native Multimodal Models • 9 items • Updated 10 days ago • 2

Gemma 4 Compression(s) - MoE

Collection of Various Compression Schemes for Gemma 4 +MoE Calibration • 4 items • Updated 8 days ago • 3