CS's picture

CS

Fonk

·

https://feelthefonk.github.io

FeelTheFonk

AI & ML interests

The Matrix has you...

Recent Activity

liked a model about 3 hours ago

Kijai/MelBandRoFormer_comfy

liked a model about 3 hours ago

Kijai/LTXV2_comfy

liked a model about 5 hours ago

RuneXX/LTX-2-Workflows

View all activity

Organizations

upvoted a collection 4 days ago

Qwen3-TTS

7 items • Updated 4 days ago • 223

upvoted an article 20 days ago

Article

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval

+1

Mar 22, 2024

•

126

upvoted a collection 27 days ago

HY-MT1.5

混元翻译模型1.5版本 • 8 items • Updated 27 days ago • 46

upvoted 2 collections about 1 month ago

sam-audio

11 items • Updated Dec 16, 2025 • 119

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 • 22 items • Updated 14 days ago • 174

upvoted 2 collections about 2 months ago

PPTAgent

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

rnj-1

5 items • Updated Dec 19, 2025 • 39

upvoted a paper 3 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 • 133

upvoted a collection 3 months ago

Granite 4.0 Nano Language Models

9 items • Updated Nov 17, 2025 • 94

upvoted an article 3 months ago

Article

Supercharge your OCR Pipelines with Open Models

+5

Oct 21, 2025

•

300

upvoted a paper 4 months ago

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

Paper • 2509.22944 • Published Sep 26, 2025 • 80

upvoted 5 collections 4 months ago

Granite Quantized Models

Quantized versions of IBM Granite models. Licensed under the Apache 2.0 license. • 44 items • Updated Nov 21, 2025 • 32

🎯 Liquid Nanos

Library of task-specific models: https://www.liquid.ai/blog/introducing-liquid-nanos-frontier-grade-performance-on-everyday-devices • 26 items • Updated about 2 hours ago • 107

DeepSeek-V3.2

4 items • Updated Dec 1, 2025 • 520

Qwen3-VL

37 items • Updated 27 days ago • 605

Granite Docling

5 items • Updated Nov 17, 2025 • 60

upvoted 4 collections 5 months ago

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 • 50

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

DeepSeek-V3.1

4 items • Updated Nov 27, 2025 • 257