Ahmet's picture

Building on HF

Ahmet

atasoglu

·

atasoglu

AI & ML interests

NLP, LLMs.

Recent Activity

liked a model about 5 hours ago

zai-org/GLM-4.7-Flash

liked a Space about 14 hours ago

magibu/embeddingmagibu-152m

liked a model about 14 hours ago

magibu/embeddingmagibu-152m

View all activity

Organizations

upvoted an article 1 day ago

Article

BF16 vs GGUF, FP8 Scaled, NVFP4 Speed & Quality Compared + ComfyUI CUDA 13 Gains + FLUX 2 Klein 9B

3 days ago

•

2

upvoted an article 4 days ago

Article

Open Responses: What you need to know

+2

5 days ago

•

74

upvoted a collection 4 days ago

TranslateGemma

3 items • Updated 5 days ago • 162

upvoted a collection 10 days ago

Qwen3-VL-Embedding

2 items • Updated 12 days ago • 56

upvoted an article 14 days ago

Article

G2P Shrinks Speech Models

Feb 5, 2025

•

83

upvoted a paper 21 days ago

TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval

Paper • 2511.16528 • Published Nov 20, 2025 • 22

upvoted an article 22 days ago

Article

Explainability and Trustworthiness in Large Language Models: Implications for Industry and Policy

23 days ago

•

1

upvoted a collection 22 days ago

Turkish-DPO-Dataset

5 items • Updated 22 days ago • 1

upvoted a collection 25 days ago

OuteTTS 1.0

14 items • Updated May 19, 2025 • 6

upvoted a collection 26 days ago

Dec 19 Releases

29 items • Updated 29 days ago • 3

upvoted 5 collections about 1 month ago

sam-audio

11 items • Updated Dec 16, 2025 • 115

Dec 12 Releases

35 items • Updated Dec 15, 2025 • 2

Molmo2 Data

Artifacts for the Molmo2 data release • 16 items • Updated 28 days ago • 33

Molmo2

Artifacts for the Molmo2 release • 6 items • Updated 28 days ago • 30

Turkish Punctuation Restoration

3 items • Updated Dec 13, 2025 • 3

upvoted 4 collections about 2 months ago

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated Dec 2, 2025 • 85

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated Dec 2, 2025 • 148

OCR VLM

4 items • Updated Aug 22, 2025 • 1

Real-time Vision Models

A collection of real-time detectors. • 19 items • Updated Nov 23, 2025 • 22

upvoted a collection 2 months ago

SAM3

4 items • Updated Nov 19, 2025 • 23