Zach Mustafa's picture

Zach Mustafa PRO

Zmu

·

AI & ML interests

None yet

Recent Activity

liked a model about 18 hours ago

microsoft/UserLM-8b

liked a Space 7 days ago

VetriVelRavi/ai-room-designer

liked a Space 11 days ago

wcy1122/DreamOmni2-Edit

View all activity

Organizations

upvoted a paper about 2 months ago

zELO: ELO-inspired Training Method for Rerankers and Embedding Models

Paper • 2509.12541 • Published Sep 16 • 4

upvoted a collection 2 months ago

OpenVision

27 items • Updated Aug 15 • 31

upvoted a collection 3 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 370

upvoted 3 collections 4 months ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 7 days ago • 227

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated 29 days ago • 84

Gemma 3n

4 items • Updated Jul 10 • 235

upvoted an article 5 months ago

Article

Accelerating LLM Code Generation Through Mask Store Streamlining

By

•

Jan 17

• 3

upvoted a collection 5 months ago

Qwen3

84 items • Updated Aug 6 • 1.4k

upvoted an article 5 months ago

Article

KV Cache from scratch in nanoVLM

Jun 4

• 98

upvoted 3 collections 5 months ago

Utilities

No crazy stuff, but useful ones for in-between steps • 16 items • Updated Mar 19 • 7

Video Understanding & Segmentation

9 items • Updated Sep 5 • 6

🎦🔀 Useful Tiny Video Converters

All spaces made to convert a video (of GIFs) to anything useful in your pipelines • 5 items • Updated Oct 3, 2024 • 7

upvoted 3 articles 5 months ago

Article

Interactive Tools for machine learning, deep learning, and math

By

•

May 26

• 47

Article

Exploring Quantization Backends in Diffusers

May 21

• 44

Article

CodeAgents + Structure: A Better Way to Execute Actions

May 28

• 79

upvoted 3 collections 6 months ago

D-FINE

State-of-the-art real-time object detection model with Apache 2.0 licence • 15 items • Updated May 5 • 55

SigLIP2

36 items • Updated Jul 10 • 92

Gemma 3 QAT

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated Jul 10 • 209

upvoted a paper 6 months ago

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Paper • 2504.19413 • Published Apr 28 • 29

upvoted a collection 7 months ago

Perception LM

7 items • Updated Apr 17 • 62