CS's picture

CS

Fonk

·

https://feelthefonk.github.io

FeelTheFonk

AI & ML interests

The Matrix has you...

Recent Activity

liked a model 2 days ago

IQuestLab/IQuest-Coder-V1-40B-Instruct

liked a model 3 days ago

Qwen/Qwen-Image-2512

liked a model 4 days ago

tencent/HY-MT1.5-7B

View all activity

Organizations

upvoted a collection 4 days ago

HY-MT1.5

混元翻译模型1.5版本 • 8 items • Updated 3 days ago • 26

upvoted a collection 18 days ago

sam-audio

11 items • Updated 18 days ago • 108

upvoted a collection 19 days ago

Health AI Developer Foundations (HAI-DEF)

Groups models released for use in health AI by Google. Read more about HAI-DEF at http://goo.gle/hai-def • 16 items • Updated 13 days ago • 140

upvoted a collection 26 days ago

PPTAgent

https://arxiv.org/abs/2501.03936 • 4 items • Updated Sep 3, 2025 • 1

upvoted a collection 28 days ago

rnj-1

5 items • Updated 15 days ago • 39

upvoted a paper about 2 months ago

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

Paper • 2511.06221 • Published Nov 9, 2025 • 132

upvoted a collection 2 months ago

Granite 4.0 Nano Language Models

9 items • Updated Nov 17, 2025 • 93

upvoted an article 2 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

Oct 21, 2025

•

289

upvoted a paper 3 months ago

SINQ: Sinkhorn-Normalized Quantization for Calibration-Free Low-Precision LLM Weights

Paper • 2509.22944 • Published Sep 26, 2025 • 79

upvoted 4 collections 3 months ago

Granite Quantized Models

Quantized versions of IBM Granite models. Licensed under the Apache 2.0 license. • 44 items • Updated Nov 21, 2025 • 29

⚛️ Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 22 items • Updated 5 days ago • 103

DeepSeek-V3.2

4 items • Updated Dec 1, 2025 • 511

Qwen3-VL

37 items • Updated 3 days ago • 553

upvoted 4 collections 4 months ago

Granite Docling

5 items • Updated Nov 17, 2025 • 60

mmBERT: a modern multilingual encoder

mmBERT is trained on 3T tokens from over 1800 languages, showing SoTA scores on benchmarks and exceptional low-resource performance • 16 items • Updated Sep 9, 2025 • 49

MobileCLIP2

MobileCLIP2: Mobile-friendly image-text models with SOTA zero-shot capabilities trained on DFNDR-2B • 37 items • Updated Sep 18, 2025 • 57

FastVLM

Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2, 2025 • 106

upvoted a collection 5 months ago

DeepSeek-V3.1

4 items • Updated Nov 27, 2025 • 257

upvoted an article 6 months ago

Article

SmolLM3: smol, multilingual, long-context reasoner

+21

Jul 8, 2025

•

741

upvoted a collection 7 months ago

Qwen3-Embedding

6 items • Updated 3 days ago • 143