Zach Mustafa PRO

Zmu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article 4 days ago

view article

Article

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

• 
• 
• +4

11 days ago

•

471

upvoted a collection 12 days ago

Qwen3.5

Collection

17 items • Updated about 16 hours ago • 710

upvoted an article 17 days ago

view article

Article

NVIDIA brings agents to life with DGX Spark and Reachy Mini

• 
• 
• +1

Jan 5

•

64

upvoted 3 collections 27 days ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Collection

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 84 items • Updated 3 days ago • 35

✂️ Abliteration

Collection

Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration • 32 items • Updated about 13 hours ago • 158

Qwen3-VL-abliterated

Collection

14 items • Updated about 13 hours ago • 29

upvoted an article 28 days ago

view article

Article

Introducing Daggr: Chain apps programmatically, inspect visually

• 
• 
• +3

Jan 29

•

103

upvoted 2 collections about 1 month ago

VibeVoice

Collection

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 8 items • Updated about 13 hours ago • 210

Qwen3-TTS

Collection

7 items • Updated Jan 22 • 314

upvoted a collection about 2 months ago

DroPE

Collection

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167) • 1 item • Updated Jan 11 • 2

upvoted a collection 2 months ago

Qwen3-Omni

Collection

6 items • Updated Dec 31, 2025 • 183

upvoted 3 articles 3 months ago

view article

Article

New in llama.cpp: Model Management

• 

Dec 11, 2025

•

126

view article

Article

Transformers v5: Simple model definitions powering the AI ecosystem

• 
• 
• +2

Dec 1, 2025

•

302

view article

Article

Continuous batching from first principles

• 
• 
• +1

Nov 25, 2025

•

340

upvoted a collection 3 months ago

Olmo 3

Collection

Artifacts for the Olmo 3 release. • 7 items • Updated about 13 hours ago • 164

upvoted 2 collections 4 months ago

V-JEPA 2

Collection

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 192

ViDoRe Benchmark V3

Collection

ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. • 8 items • Updated Jan 14 • 20

upvoted a paper 6 months ago

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

Paper • 2509.12541 • Published Sep 16, 2025 • 6

upvoted a collection 6 months ago

OpenVision

Collection

27 items • Updated Aug 15, 2025 • 33

upvoted a collection 7 months ago

DINOv3

Collection

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 522