🏗️ Building on HF

Ahmet

atasoglu

·

https://atasoglu.github.io/

AI & ML interests

NLP, LLMs.

Recent Activity

liked a model 1 day ago

MiniMaxAI/MiniMax-H3

liked a model 1 day ago

inclusionAI/Ling-3.0-tiny

liked a model 1 day ago

meta-models/Muse-Glimmer-30B

View all activity

Organizations

upvoted a paper 9 days ago

Bekko Embedding: Parameter-Efficient Multilingual Retrieval with Ultra-Compact Encoders

Paper • 2607.25180 • Published 15 days ago • 2

upvoted an article 9 days ago

Article

Bekko Embedding: how small can a multilingual retrieval model be?

hotchpotch

•

14 days ago

• 6

upvoted a collection 23 days ago

ModernBERT-TR

A 150M-parameter Turkish encoder family of base and downstream task models. • 20 items • Updated 23 days ago • 12

upvoted an article 27 days ago

Article

Welcome Inkling by Thinking Machines

+3

burtenshaw, merve, pcuenq, ariG23498, andito

•

28 days ago

• 162

upvoted 3 articles about 2 months ago

Article

Adding MCP Tools to Reachy Mini

alozowski

•

Jun 3

• 26

Article

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

sergiopaniego, ariG23498

•

May 25

• 137

Article

Agentic Resource Discovery: Let agents search

burtenshaw, evalstate

•

Jun 17

• 21

upvoted 3 collections 2 months ago

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 1 day ago • 118

Gemma 4 QAT Mobile

4 items • Updated 22 days ago • 49

Gemma 4 QAT Q4_0

19 items • Updated 22 days ago • 156

upvoted an article 3 months ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

manu

•

Jul 17, 2025

• 77

upvoted 4 collections 3 months 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 16 days ago • 37

privacy-filter

OpenAI's privacy-filter fine0tuned models • 12 items • Updated 30 days ago • 12

Gemma-4 Assistant (MTP)

4 items • Updated May 5 • 29

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 • 21

upvoted 5 collections 4 months ago

Privacy Filter

3 items • Updated Apr 22 • 1

Qwen3.6

4 items • Updated Apr 22 • 478

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 • 74

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 1 day ago • 255

Gemma 4

16 items • Updated 22 days ago • 1.07k