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

upvoted an article about 13 hours ago

AI evals are becoming the new compute bottleneck

upvoted an article about 13 hours ago

Pallas for people who know JAX but not kernels yet

liked a model about 13 hours ago

prithivMLmods/Q3.5-27B-Opus-DA

View all activity

Organizations

prithivMLmods 's Spaces 61

Z Image Turbo LoRA DLC

Demo of a Collection of Impressive LoRAs for Z-Image-Turbo

SAGE Video Reasoning

Smart Any-Horizon Agents for Long Video Reasoning. [SAGE]

Super OCRs Demo

Experiment with small super OCR models here.

DeepSeek OCR Experimental

Testing for the latest transformers (DeepSeek-OCR).

NVIDIA Nemotron Parse OCR

understand document semantics, extract text and tables.

Molmo2 HF Demo

Molmo2 - Image, Video (QA, Pointing & Tracking)

Qwen-Image-2512-LoRA-DLC

Qwen-Image-2512 + LoRAs

POINTS Reader OCR

Vision-Language Models for Document Conversion

TRELLIS.2-Text-to-3D (Rerun)

Text-to-Image → 3D or Image-to-3D

Multimodal VLM v1.0

OCR, VQA, Thinking and Object Detection.

Florence-2-Image-Caption-Daggr

Image Caption : Florence-2 Models

Qwen Image LoRA DLC

Qwen Image LoRA's

Florence2 Vision Models

Florence-2 vision models demo. (transformers)

CUA GUI Operator

Ultra-compact Computer-Use Agent [GUI Localization]

Florence-2 Models

Florence-2-large / Florence-2-base

Multimodal VLM Thinking

Lumian-VLR / VisionThink / MiniCPM-V / Typhoon-OCR / olmOCR

Qwen3 VL HF Demo

Object Detection, Visual Grounding, Keypoint Detection

Qwen3-VL-abliterated-MAX-Fast

Unredacted: Ask Anything with Near-Zero Refusal Rates

DeepSeek-OCR-2-Demo

DeepSeek-OCR 2: Visual Causal Flow

core OCR

coreOCR / Camel-Doc-OCR / docscopeOCR / MonkeyOCR

Multimodal OCR3

Chandra-OCR / Nanonets-OCR2 / olmOCR-2 / Dots.OCR

Cheers HF Demo

Unified Multimodal Comprehension and Generation

DocScope-R1

Cosmos-R1 / docscopeOCR / Captioner-7B / visionOCR-3B

VisionScope-R2

DeepCaption / SkyCaptioner / SpaceThinker / Core / SpaceOm