Nikolay Kozlov's picture

Nikolay Kozlov

NikolayKozloff

·

AI & ML interests

None yet

Organizations

None yet

NikolayKozloff's activity

upvoted 3 collections 1 day ago

Qwen2.5-Coder

Code-specific model series based on Qwen2.5 • 40 items • Updated 1 day ago • 162

🍓 Ichigo v0.4

The experimental family designed to train LLMs to understand sound natively. • 2 items • Updated 2 days ago • 4

Open LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 58 items • Updated 14 minutes ago • 437

upvoted a collection 4 days ago

OpenCoder

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 4 items • Updated 4 days ago • 52

upvoted a collection 7 days ago

OS-Atlas

OS-Atlas series models • 7 items • Updated 3 days ago • 8

upvoted a collection 11 days ago

QTIP Quantized Models

See https://github.com/Cornell-RelaxML/qtip • 27 items • Updated 16 days ago • 5

upvoted 2 collections 12 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 8 days ago • 163

MobileLLM

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 8 items • Updated 6 days ago • 93

upvoted a collection 19 days ago

INTELLECT-1 Dataset

INTELLECT-1 Training dataset • 5 items • Updated Oct 8 • 9

upvoted a collection 21 days ago

steiner-preview

Reasoning models trained on synthetic data using reinforcement learning. • 3 items • Updated 24 days ago • 23

upvoted a collection 22 days ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 8 days ago • 86

upvoted a collection 23 days ago

v4

18 items • Updated 24 days ago • 23

upvoted a collection 26 days ago

Arch-Function

6 items • Updated 14 days ago • 7

upvoted 2 collections 28 days ago

ApolloMoE & Apollo2

English, Chinese, French, Hindi, Spanish, Arabic, Russian, Japanese, Korean, German, Italian, Portuguese and 38 Minor Languages • 7 items • Updated 29 days ago • 3

LoLCATS

Linearizing LLMs with high quality and efficiency. We linearize the full Llama 3.1 model family -- 8b, 70b, 405b -- for the first time! • 4 items • Updated 30 days ago • 14

upvoted 3 collections about 1 month ago

DCLM

DCLM Models + Datasets • 7 items • Updated Jul 22 • 41

Qwen2

Qwen2 language models, instruction-tuned models of 3 sizes: 0.5B, 1.5B, 7B. • 3 items • Updated Jun 13 • 1

Arctic

A collection of pre-trained dense-MoE Hybrid transformer models • 2 items • Updated Apr 24 • 23

upvoted an article about 1 month ago

Article

Introducing Würstchen: Fast Diffusion for Image Generation

Sep 13, 2023

• 11

upvoted a collection about 1 month ago

Emu3

5 items • Updated 18 days ago • 64