🌀 Building on HF

Prithiv Sakthi PRO

prithivMLmods

hugging-science

·

https://prithivsakthiur.github.io/

AI & ML interests

computer vision, nlp, multimodality - HuggingFace Fellow ML 🤗

Recent Activity

updated a collection about 8 hours ago

liked a model about 8 hours ago

prithivMLmods/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF

published a model about 8 hours ago

prithivMLmods/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-GGUF

View all activity

Organizations

upvoted a changelog 2 days ago

Hugging Face Changelog

A New Main Search UI

2 days ago

• 77

upvoted a paper 3 days ago

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Paper • 2604.18556 • Published Apr 20 • 26

upvoted a collection 3 days ago

ERNIE-5.5-Flash

Collection of ERNIE-5.5-Flash models. • 2 items • Updated 4 days ago • 27

upvoted 2 collections 4 days ago

MTP-Repacked

Collection of MTP-repacked weights for faster speculative decoding and accelerated local inference. • 6 items • Updated 1 day ago • 1

CCORE 3D-Coder Model Compressions

Collection of CCORE Qwen3.5 Models MTP Variants, and GGUF Quantizations. • 6 items • Updated 1 day ago • 1

upvoted 3 collections 6 days ago

Chandra-OCR Model Compressions

Collection of Chandra-OCR Model GGUF Quantizations and Compressions • 5 items • Updated 1 day ago • 1

November 2026

Collection of Collections and Models — November 2026 • 39 items • Updated about 8 hours ago • 1

NVIDIA Blackwell-Optimized

Collection of NVIDIA Blackwell-Optimized Calibration and Quantizations (NVFP4, MXFP4, and More) • 34 items • Updated about 15 hours ago • 1

upvoted 2 papers 6 days ago

Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use

Paper • 2610.40738 • Published 11 days ago • 38

FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation

Paper • 2610.36545 • Published 13 days ago • 35

upvoted a collection 7 days ago

LFM3 GGUF

Collection of LFM3 GGUF Quantizations • 4 items • Updated 1 day ago • 1

upvoted a collection 8 days ago

VIGOR

VIGOR — Vision Intelligence and Guardrail Oriented Reasoning • 6 items • Updated 1 day ago • 1

upvoted 2 papers 9 days ago

PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Paper • 2610.37381 • Published 13 days ago • 157

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 15 days ago • 40

upvoted 3 articles 9 days ago

Article

Clover\-35B\-A3B\-Preview: A New Way for Intelligence

Diffuspace

•

10 days ago

• 20

Article

A curriculum for post-training agents

huggingface

•

19 days ago

• 110

Article

Granite Switch 4.1.1 — Update models like you update software

ibm-granite

•

10 days ago

• 36

upvoted 3 collections 12 days ago

ZwZ2 — inclusionAI GGUF

Collection of ZwZ2 Multimodal Model Compressions • 4 items • Updated 1 day ago • 1

Qwen 3.5 / 3.6 / 3.8 NVFP4 [Only]

Collection of NVFP4 Compressions from Qwen3.5 to Qwen3.8 • 10 items • Updated about 21 hours ago • 1

MiniCPM-OCR

Fast, accurate OCR with correctness assessment. • 10 items • Updated 11 days ago • 18