Ahmet's picture

Ahmet

atasoglu

·

atasoglu

AI & ML interests

NLP, LLMs.

Recent Activity

upvoted a collection 3 days ago

upvoted a collection 5 days ago

liked a model 6 days ago

google/Gemma-Embeddings-v1.0

View all activity

Organizations

atasoglu's activity

upvoted a collection 3 days ago

ModernBERT

Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated 3 days ago • 75

upvoted a collection 5 days ago

Falcon3

Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B parameters. • 40 items • Updated 3 days ago • 69

upvoted 4 collections 14 days ago

SigLIP

Contrastive (sigmoid) image-text models from https://arxiv.org/abs/2303.15343 • 10 items • Updated 9 days ago • 46

DataGemma Release

A series of pioneering open models that help ground LLMs in real-world data through Data Commons. • 2 items • Updated 9 days ago • 81

EuroLLM

4 items • Updated 20 days ago • 24

Dec 6 Releases 🎄

28 items • Updated 13 days ago • 9

upvoted a collection 15 days ago

Llama 3.3 (All Versions)

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. • 3 items • Updated 14 days ago • 27

upvoted a paper 17 days ago

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published 18 days ago • 118

upvoted a collection 17 days ago

PaliGemma 2 Release

Vision-Language Models available in multiple 3B, 10B and 28B variants. • 23 items • Updated 9 days ago • 118

upvoted a collection 18 days ago

Unsloth 4-bit Dynamic Quants

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 7 items • Updated 8 days ago • 20

upvoted a collection 19 days ago

🧠 Reasoning Models

5 items • Updated 6 days ago • 31

upvoted 2 collections 22 days ago

LLM2CLIP

LLM2CLIP makes SOTA pretrained CLIP modal more SOTA ever. • 10 items • Updated 11 days ago • 47

QwQ

Qwen with Questions • 2 items • Updated 24 days ago • 42

upvoted a collection 25 days ago

SmolVLM

State-of-the-art compact VLMs for on-device applications: Base, Synthetic, and Instruct • 5 items • Updated 26 days ago • 29

upvoted 2 collections 29 days ago

AIMv2

A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated 30 days ago • 67

Nov 22 Releases ❄️

45 items • Updated 30 days ago • 5

upvoted a paper about 1 month ago

LLaVA-o1: Let Vision Language Models Reason Step-by-Step

Paper • 2411.10440 • Published Nov 15 • 110

upvoted a collection about 1 month ago

Nov 15 Releases 🍂

15 items • Updated Nov 15 • 6

upvoted 2 collections about 2 months ago

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 9 items • Updated 25 days ago • 99

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 20 days ago • 195