Sitam Meur's picture

Building on HF

Sitam Meur

sitammeur

·

https://linktr.ee/sitammeur

AI & ML interests

Real-world problem-solving using AI, machine learning, and deep learning. Fields like Natural Language Processing, Computer Vision, etc.

Recent Activity

updated a Space 3 days ago

sitammeur/LFM2.5-Thinking-WebGPU

updated a Space 3 days ago

sitammeur/LFM2.5-JP-WebGPU

liked a Space 10 days ago

sitammeur/LFM2.5-Thinking-WebGPU

View all activity

Organizations

sitammeur 's Spaces 22

LFM2.5 Thinking WebGPU

LFM2.5 reasoning LLM within web using Transformers.js & ONNX

LFM2.5 JP WebGPU

LFM2.5-JP LLM works in browsers using Transformers.js & ONNX

Gemma 3 WebGPU

Gemma3 LLM operates in browsers via Transformers.js & ONNX

Prompt Enhancer

Make short prompt into context-rich, powered by on-device AI

ClassyText

Zero-shot text classification using ModernBERT-large

GLiNER PII

Zero-shot PII/PHI recognition app using NVIDIA's GLiNER-PII

GLiClass Playground

Zero-shot text classification using Knowledgator's GLiClass

MedSigLIP Classifier

Zero-shot classification of medical images using MedSigLIP

T5Gemma Captioner

Image Captioning with T5Gemma2 encoder-decoder img-txt Model

Paligemma Captioner

Image Captioning with PaliGemma 2 Vision Language Model

ModernBERT WebGPU

ModernBERT classifier in browsers via Transformers.js & ONNX

Qwen 2.5 WebGPU

Qwen2.5 LLM operates in browsers via Transformers.js & ONNX

GLiNER2 Suite

GLiNER2 multi-task capabilities with NER and Classification

PicQ

Demo for MiniCPM-o 2.6 to answer questions about images

VidiQA

Demo for MiniCPM-o 2.6 to answer questions about videos

DepthLens

Generate depth maps from images

Gemma Llamacpp

Gemma 3: Google's multimodal, multilingual, long context LLM

Qwen-Coder Llamacpp

Qwen2.5-Coder: Family of LLMs excels in code, debugging, etc

YoloPose

Showcasing Yolo, enabling human pose detection

TextSnap

Florence 2 used in OCR to extract & visualize text

ColVision Gemini Retrieval

Redefining Multimodal RAG with ColQwen2.5 (ColPali) & Gemini

ModernVBERT Qwen Retrieval

Redefining Multimodal RAG with ColModernVBERT & Qwen 3 model