Nikolay Kozlov's picture

Nikolay Kozlov

NikolayKozloff

·

AI & ML interests

None yet

Recent Activity

liked a model about 4 hours ago

Qwen/Qwen3-Coder-30B-A3B-Instruct

liked a model about 4 hours ago

black-forest-labs/FLUX.1-Krea-dev

liked a Space about 5 hours ago

CohereLabs/command-a-vision

View all activity

Organizations

upvoted a collection about 6 hours ago

X-Omni Models

2 items • Updated 2 days ago • 2

upvoted a paper about 10 hours ago

Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance

Paper • 2507.22448 • Published 1 day ago • 39

upvoted a collection 3 days ago

GLM-4.5

8 items • Updated 3 days ago • 156

upvoted a collection 14 days ago

Seed-X

A powerful open-source multilingual translation language model series, including instruction and reasoning models. • 6 items • Updated 3 days ago • 60

upvoted a collection 19 days ago

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 15 items • Updated 3 days ago • 81

upvoted 2 collections 22 days ago

T5Gemma

32 items • Updated 22 days ago • 59

Falcon-H1

Falcon-H1 Family of Hybrid-Head Language Models (Transformer-SSM), including 0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B (pretrained & instruction-tuned). • 38 items • Updated about 15 hours ago • 48

upvoted a collection 23 days ago

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 12 items • Updated 7 days ago • 66

upvoted an article 23 days ago

Article

SmolLM3: smol, multilingual, long-context reasoner

By

and 22 others •

24 days ago

• 600

upvoted a collection 24 days ago

Jamba 1.7

The AI21 Jamba family of models are hybrid SSM-Transformer foundation models, blending speed, efficient long context processing, and accuracy. • 4 items • Updated 29 days ago • 10

upvoted a collection 28 days ago

Text-To-Speech

https://kyutai.org/next/tts • 3 items • Updated 29 days ago • 14

upvoted a collection 30 days ago

GLM-4.1V-Thinking

5 items • Updated 29 days ago • 52

upvoted an article about 1 month ago

Article

Welcome aMUSEd: Efficient Text-to-Image Generation

By

and 3 others •

Jan 4, 2024

• 12

upvoted 6 collections about 1 month ago

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 25 items • Updated 20 days ago • 157

Gemma 3n

4 items • Updated 22 days ago • 200

Arch-Agent

12 items • Updated Jun 20 • 4

dots.llm1

2 items • Updated Jun 11 • 17

Poro 2

8 items • Updated Jun 19 • 4

MiniMax-M1

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated 28 days ago • 110

upvoted a collection about 2 months ago

Perception LM

7 items • Updated Apr 17 • 59