Ahmet's picture

Ahmet

atasoglu

·

atasoglu

AI & ML interests

NLP, LLMs.

Recent Activity

liked a model 1 day ago

Qwen/Qwen3-Embedding-4B

liked a model 1 day ago

Qwen/Qwen3-Embedding-8B

liked a model 1 day ago

Qwen/Qwen3-Embedding-4B-GGUF

View all activity

Organizations

atasoglu's activity

upvoted 2 collections 1 day ago

Qwen3-Embedding

6 items • Updated 1 day ago • 57

Qwen3-Reranker

3 items • Updated 1 day ago • 34

upvoted a paper 7 days ago

Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Paper • 2505.23747 • Published 8 days ago • 66

upvoted an article 8 days ago

Article

Manus AI: The Best Autonomous AI Agent Redefining Automation and Productivity

By

•

Mar 6

• 171

upvoted an article 19 days ago

Article

🥬 LettuceDetect Goes Multilingual: Fine-tuning EuroBERT on Synthetic Translations

By

and 1 other •

19 days ago

• 9

upvoted a collection 19 days ago

RAGTruth LLM Translations

This collection includes our translated training data that we've used to create multilingual hallucination detection models. • 8 items • Updated 19 days ago • 3

upvoted an article 25 days ago

Article

Vision Language Models (Better, Faster, Stronger)

By

and 4 others •

26 days ago

• 417

upvoted a collection 28 days ago

Trendyol Embedding v1.0

1 item • Updated about 1 month ago • 2

upvoted a collection 29 days ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 65 items • Updated 8 days ago • 150

upvoted 3 collections about 1 month ago

Releases Apr 21 & May 2

54 items • Updated May 6 • 3

Qwen3

40 items • Updated 17 days ago • 739

Describe Anything

Multimodal Large Language Models for Detailed Localized Image and Video Captioning • 7 items • Updated about 12 hours ago • 50

upvoted 2 collections about 2 months ago

April 16 Releases

2 items • Updated Apr 16 • 1

Trendyol LLM v4.0

Qwen2.5-7B based finetuned models • 1 item • Updated Apr 9 • 2

upvoted a paper about 2 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 188

upvoted 3 collections 2 months ago

FastRTC Custom UIs

A collection of FastRTC demos that showcase how to built a Custom UI for your server • 4 items • Updated Apr 7 • 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 Apr 7 • 4

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 8 days ago • 46

upvoted a paper 2 months ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Paper • 2503.10582 • Published Mar 13 • 23

upvoted a collection 2 months ago

Llama 4

Llama 4 release • 13 items • Updated Apr 29 • 522