Ahmet's picture

Ahmet

atasoglu

·

atasoglu

AI & ML interests

NLP, LLMs.

Recent Activity

liked a dataset about 19 hours ago

nvidia/describe-anything-dataset

liked a dataset about 19 hours ago

nvidia/DLC-Bench

liked a model about 19 hours ago

nvidia/DAM-3B-Self-Contained

View all activity

Organizations

atasoglu's activity

upvoted a collection about 19 hours ago

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 6 items • Updated 1 day ago • 30

upvoted a collection 8 days ago

April 16 Releases

2 items • Updated 8 days ago • 1

upvoted a collection 14 days ago

Trendyol LLM v4.0

Qwen2.5-7B based finetuned models • 1 item • Updated 15 days ago • 2

upvoted a paper 16 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 17 days ago • 171

upvoted 2 collections 17 days ago

FastRTC Custom UIs

A collection of FastRTC demos that showcase how to built a Custom UI for your server • 4 items • Updated 17 days ago • 2

EchoLLaMA: 3D-to-Speech with Multimodal AI

This collection contains the models and datasets used in EchoLLaMA: 3D-to-Speech with Multimodal AI paper. • 4 items • Updated 17 days ago • 4

upvoted a collection 18 days ago

Llama 4

Meta's new Llama 4 multimodal models, Scout & Maverick. Includes Dynamic GGUFs, 16-bit & Dynamic 4-bit uploads. Run & fine-tune them with Unsloth! • 15 items • Updated about 10 hours ago • 43

upvoted a paper 18 days ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Paper • 2503.10582 • Published Mar 13 • 23

upvoted a collection 19 days ago

Llama 4

Llama 4 release • 10 items • Updated 19 days ago • 447

upvoted 2 collections 21 days ago

Google's Gemma models family

279 items • Updated 6 days ago • 169

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 6 days ago • 161

upvoted a paper 21 days ago

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Paper • 2412.09401 • Published Dec 12, 2024 • 3

upvoted a collection 25 days ago

March 28 Releases

11 items • Updated 28 days ago • 3

upvoted 4 collections about 1 month ago

MambaVision

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 13 items • Updated 1 day ago • 31

March 21 Releases

39 items • Updated Mar 22 • 10

Gemma 3 Release

24 items • Updated 6 days ago • 342

EuroBERT

Scaling Multilingual Encoders for European Languages • 4 items • Updated Mar 10 • 11

upvoted a collection about 2 months ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated Feb 25 • 82