sakuma's picture

sakuma

sakumaXIII

·

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

AuriAetherwiing/G4-E4B-Musica-v1

liked a model 1 day ago

SicariusSicariiStuff/IBM_granite-4.1-8b_Abliterated

liked a model 3 days ago

Zyphra/ZAYA1-8B

View all activity

Organizations

None yet

upvoted 3 collections 4 days ago

Musica

Versatile creative finetunes. • 4 items • Updated 6 days ago • 1

LARQL Vindex Library

Every LARQL vindex in one place — browse, client, server, and full mirrors for each supported model. • 8 items • Updated 5 days ago • 2

Gemma 4 26B A4B It — LARQL Vindex

All deployment variants of Gemma 4 26B A4B It as LARQL vindexes — full, client, server, browse. • 2 items • Updated 5 days ago • 4

upvoted a collection 6 days ago

Neon Veil

3 items • Updated 9 days ago • 1

upvoted a collection 16 days ago

DeepSeek-V4

4 items • Updated 17 days ago • 624

upvoted an article 21 days ago

Article

Building a Fast Multilingual OCR Model with Synthetic Data

23 days ago

•

32

upvoted 2 articles 24 days ago

Article

Multimodal Embedding & Reranker Models with Sentence Transformers

Apr 9

•

58

Article

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

25 days ago

•

70

upvoted a collection 25 days ago

NVIDIA Ising

NVIDIA Ising is a new Model Family to enable building useful Quantum Computers with AI. • 4 items • Updated 2 days ago • 21

upvoted a collection 26 days ago

Gemma Family

LiteRT models in the Gemma Family • 19 items • Updated 6 days ago • 74

upvoted 4 collections about 1 month ago

Qwen3.5-abliterated

22 items • Updated Apr 6 • 80

Gemma 4

12 items • Updated 5 days ago • 784

Bonsai

1-bit Bonsai models • 7 items • Updated 23 days ago • 191

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 199

upvoted a paper about 1 month ago

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Paper • 2504.19874 • Published Apr 28, 2025 • 34

upvoted 3 collections about 2 months ago

Favorite Models

Mostly uncensored models for low VRAM budget • 20 items • Updated 1 day ago • 5

Uncensored 12Bs

Fully uncensored 12B models • 7 items • Updated Mar 6 • 2

Mistral Small 4

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated Mar 16 • 73

upvoted an article 2 months ago

Article

LeRobot v0.5.0: Scaling Every Dimension

+8

Mar 9

•

41

upvoted an article 3 months ago

Article

Introducing Marvis TTS: Real-Time Streaming Speech Synthesis

Aug 27, 2025

•

19