Sergey Zubrilin's picture

Sergey Zubrilin

hiauiarau

·

AI & ML interests

None yet

Recent Activity

liked a model about 3 hours ago

ai-forever/sage-v1.1.0

liked a model about 9 hours ago

reducto/RolmOCR

liked a model about 16 hours ago

google/gemma-3-1b-it-qat-q4_0-gguf

View all activity

Organizations

hiauiarau's activity

upvoted a collection 1 day ago

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 2 days ago • 88

upvoted a collection 3 days ago

Nomic Embed Multimodal

Multimodal models allowing you to search over interleaved text, PDFs, charts, and images! • 14 items • Updated 1 day ago • 15

upvoted a collection 10 days ago

Qwen2.5-Omni

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5 • 3 items • Updated 10 days ago • 77

upvoted an article 19 days ago

Article

Convert Transformers to ONNX with Hugging Face Optimum

Jun 22, 2022

• 5

upvoted a collection 20 days ago

GME Models

General Multimodal Embedding Models Released by Tongyi Lab of Alibaba Group • 3 items • Updated Dec 24, 2024 • 6

upvoted a paper 25 days ago

Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders

Paper • 2503.03601 • Published Mar 5 • 226

upvoted 3 collections 25 days ago

Gemma 3 Release

17 items • Updated 2 days ago • 310

GTE ModernBERT

GTE Models Based on ModernBERT • 2 items • Updated Jan 21 • 16

C4AI Aya Vision

Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated Mar 4 • 68

upvoted a collection 28 days ago

Nomic Embed v2

Multilingual Embedding Models • 4 items • Updated Feb 15 • 18

upvoted a collection about 1 month ago

Babel

Open Multilingual Large Language Models Serving Over 90% of Global Speakers • 7 items • Updated 3 days ago • 17

upvoted an article about 1 month ago

Article

A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality

Mar 4

• 72

upvoted a collection about 1 month ago

Ultravox v0.5

Ultravox is a multimodal Speech LLM built around different pretrained LLMs (frozen) and the whisper-large-v3-turbo (fine-tuned) backbone. • 3 items • Updated Feb 10 • 11

upvoted an article about 1 month ago

Article

PaliGemma 2 Mix - New Instruction Vision Language Models by Google

Feb 19

• 66

upvoted a collection about 1 month ago

PaliGemma 2 Mix

13 items • Updated 2 days ago • 60

upvoted an article 2 months ago

Article

Open-source DeepResearch – Freeing our search agents

Feb 4

• 1.21k

upvoted 2 collections 2 months ago

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated Feb 26 • 111

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 11 items • Updated 5 days ago • 436

upvoted an article 2 months ago

Article

Finally, a Replacement for BERT: Introducing ModernBERT

Dec 19, 2024

• 594