Nikolay Kozlov's picture

Nikolay Kozlov

NikolayKozloff

·

AI & ML interests

None yet

Recent Activity

liked a Space about 17 hours ago

LiquidAI/LFM2.5-1.2B-Thinking-WebGPU

liked a model about 22 hours ago

PicoKittens/PicoStories-853K

liked a model about 22 hours ago

PicoKittens/PicoMistral-23M

View all activity

Organizations

upvoted a collection 3 days ago

RWKV v7

9 items • Updated Mar 17, 2025 • 10

upvoted a collection 15 days ago

MioTTS

12 items • Updated 13 days ago • 9

upvoted a collection 28 days ago

LingBot-World

1 item • Updated 29 days ago • 35

upvoted 2 collections 29 days ago

Kakugo datasets

Synthetic datasets in low resource languages created using the Kakugo pipeline (https://github.com/Peter-Devine/kakugo) • 55 items • Updated 29 days ago • 1

Kakugo models

Small language models trained to interact in various low-resource languages created using the Kakugo pipeline (https://github.com/Peter-Devine/kakugo) • 56 items • Updated 29 days ago • 1

upvoted a collection 30 days ago

Open Coding Agents

12 items • Updated 16 days ago • 49

upvoted a collection about 1 month ago

Stable-DiffCoder

2 items • Updated Jan 22 • 5

upvoted an article about 1 month ago

Article

svara-TTS — Open Multilingual TTS for India’s Voices

Oct 27, 2025

•

21

upvoted 3 collections about 1 month ago

Qwen3-TTS

7 items • Updated Jan 22 • 310

Falcon-H1-Tiny

A series of extremely small, yet powerful language models redefining capabilities at small scale • 22 items • Updated Jan 15 • 35

TranslateGemma

3 items • Updated Jan 15 • 215

upvoted an article about 1 month ago

Article

Emergent Semantics Beyond Token Embeddings: A GPT-like Transformer Learns with Frozen 16‑D Binary Token-ID Embeddings (n_embed=16)

Jan 6

•

1

upvoted a collection about 1 month ago

WeDLM

4 items • Updated 22 days ago • 17

upvoted 2 collections about 2 months ago

Jamba2

Jamba2 is a highly-efficient open source family of language models built for maximum reliability and steerability in the enterprise. • 3 items • Updated Jan 8 • 5

Qwen3-VL-Reranker

2 items • Updated Jan 8 • 39

upvoted an article about 2 months ago

Article

Introducing Falcon H1R 7B

Jan 5

•

58

upvoted a paper about 2 months ago

Scaling Open-Ended Reasoning to Predict the Future

Paper • 2512.25070 • Published Dec 31, 2025 • 19

upvoted 2 collections about 2 months ago

HyperCLOVA X SEED

HyperCLOVA X SEED is NAVER's lightweight open-source lineup with a strong focus on Korean language performance • 6 items • Updated Dec 24, 2025 • 41

HY-MT1.5

混元翻译模型1.5版本 • 8 items • Updated 22 days ago • 47

upvoted a collection 2 months ago

Openhands Trajectories

Dataset of 67,074 OpenHands trajectories collected with Qwen3-Coder-480B-A35B-Instruct and two RFT checkpoints trained on the data • 3 items • Updated Dec 23, 2025 • 6