Ahmet's picture

Ahmet

atasoglu

·

atasoglu

AI & ML interests

NLP, LLMs.

Recent Activity

liked a model about 6 hours ago

microsoft/MAI-DS-R1

liked a dataset about 6 hours ago

zwhe99/DeepMath-103K

liked a dataset about 8 hours ago

openai/mrcr

View all activity

Organizations

atasoglu's activity

upvoted a collection 6 days ago

April 16 Releases

2 items • Updated 6 days ago • 1

upvoted a collection 12 days ago

Trendyol LLM v4.0

Qwen2.5-7B based finetuned models • 1 item • Updated 13 days ago • 2

upvoted a paper 14 days ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 15 days ago • 168

upvoted 2 collections 15 days ago

FastRTC Custom UIs

A collection of FastRTC demos that showcase how to built a Custom UI for your server • 4 items • Updated 15 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 15 days ago • 4

upvoted a collection 16 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 1 day ago • 43

upvoted a paper 16 days ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Paper • 2503.10582 • Published Mar 13 • 22

upvoted a collection 17 days ago

Llama 4

Llama 4 release • 10 items • Updated 17 days ago • 442

upvoted 2 collections 19 days ago

Google's Gemma models family

279 items • Updated 4 days ago • 167

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 4 days ago • 157

upvoted a paper 20 days ago

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

Paper • 2412.09401 • Published Dec 12, 2024 • 3

upvoted a collection 24 days ago

March 28 Releases

11 items • Updated 26 days ago • 3

upvoted a collection 29 days ago

MambaVision

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models. • 13 items • Updated 8 days ago • 31

upvoted 3 collections about 1 month ago

March 21 Releases

39 items • Updated Mar 22 • 10

Gemma 3 Release

24 items • Updated 4 days ago • 341

EuroBERT

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

upvoted 2 collections about 2 months ago

SmolVLM2 📺 Smallest video LM ever 🤏🏻

11 items • Updated Feb 25 • 82

Phi-4

Phi-4 family of small language and multi-modal models. • 9 items • Updated 5 days ago • 117