Ahmet's picture

🏗️ Building on HF

Ahmet

atasoglu

·

https://atasoglu.github.io/

AI & ML interests

NLP, LLMs.

Recent Activity

upvoted an article about 13 hours ago

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

liked a model 1 day ago

Vyvo/Vyvo-Multilingual-v0.1

liked a model 1 day ago

Vyvo/Vyvo-Multilingual-JA-FT-v0.1

View all activity

Organizations

upvoted an article about 13 hours ago

Article

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

sergiopaniego, ariG23498

•

about 1 month ago

• 120

upvoted an article 5 days ago

Article

Agentic Resource Discovery: Let agents search

burtenshaw, evalstate

•

8 days ago

• 15

upvoted 3 collections 19 days ago

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 9 days ago • 93

Gemma 4 QAT Mobile

4 items • Updated 19 days ago • 43

Gemma 4 QAT Q4_0

19 items • Updated 19 days ago • 137

upvoted an article about 1 month ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

manu

•

Jul 17, 2025

• 77

upvoted a collection about 1 month ago

jina-embeddings-v5-omni

Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated May 12 • 36

upvoted 3 collections about 2 months ago

privacy-filter

OpenAI's privacy-filter fine0tuned models • 6 items • Updated 3 days ago • 10

Gemma-4 Assistant (MTP)

4 items • Updated May 5 • 28

Mistral Medium 3.5

Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 19

upvoted 3 collections 2 months ago

Privacy Filter

3 items • Updated Apr 22 • 1

Qwen3.6

4 items • Updated Apr 22 • 417

gpt-oss-safeguard

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss • 2 items • Updated Oct 29, 2025 • 73

upvoted 2 collections 3 months ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 36 items • Updated 9 days ago • 222

Gemma 4

15 items • Updated 14 days ago • 987

upvoted an article 3 months ago

Article

Tokenization is Killing our Multilingual LLM Dream

omarkamali

•

Mar 15

• 12

upvoted 2 collections 3 months ago

Holo2

Holo2 - Cost-Efficient Models for Cross-Platform Computer-Use Agents • 4 items • Updated Feb 2 • 27

Inference Optimized Checkpoints (with Model Optimizer)

A collection of generative models quantized and optimized for inference with Model Optimizer. • 77 items • Updated about 1 hour ago • 172

upvoted 2 collections 4 months ago

ERDES — Ocular Ultrasound Classification All Tasks

ERDES benchmark: 8 architectures × 5 ocular ultrasound classification tasks. Paper: arXiv:2508.04735 | Dataset: pcvlab/erdes • 59 items • Updated Mar 5 • 2

magibu-q-series

5 items • Updated Mar 6 • 3