Zach Mustafa's picture

Zach Mustafa PRO

Zmu

·

AI & ML interests

None yet

Recent Activity

liked a dataset 1 day ago

daniel3303/StoryReasoningAdversarialDPO

liked a dataset 1 day ago

daniel3303/GroundCap

liked a model 1 day ago

daniel3303/QwenStoryteller2

View all activity

Organizations

upvoted an article 2 days ago

Article

LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling

Feb 12

•

52

upvoted an article 3 days ago

Article

Guided Decoding and Its Critical Role in Retrieval-Augmented Generation: A Deep Dive into Structured LLM Outputs

Sep 8, 2025

•

17

upvoted a collection 3 days ago

AutoGaze

7 items • Updated 9 days ago • 8

upvoted an article 10 days ago

Article

State of Open Source on Hugging Face: Spring 2026

11 days ago

•

72

upvoted an article 30 days ago

Article

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

+4

Feb 20

•

490

upvoted a collection about 1 month ago

Qwen3.5

21 items • Updated 19 days ago • 1.33k

upvoted an article about 1 month ago

Article

NVIDIA brings agents to life with DGX Spark and Reachy Mini

+1

Jan 5

•

65

upvoted 3 collections about 2 months ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 103 items • Updated 4 days ago • 44

✂️ Abliteration

Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration • 32 items • Updated 26 days ago • 164

Qwen3-VL-abliterated

14 items • Updated 26 days ago • 31

upvoted an article about 2 months ago

Article

Introducing Daggr: Chain apps programmatically, inspect visually

+3

Jan 29

•

106

upvoted 2 collections 2 months ago

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 8 items • Updated 26 days ago • 214

Qwen3-TTS

7 items • Updated Jan 22 • 334

upvoted 2 collections 3 months ago

DroPE

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167) • 1 item • Updated Jan 11 • 3

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 189

upvoted 3 articles 4 months ago

Article

New in llama.cpp: Model Management

Dec 11, 2025

•

130

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

Dec 1, 2025

•

307

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

351

upvoted a collection 4 months ago

Olmo 3

Artifacts for the Olmo 3 release. • 7 items • Updated 26 days ago • 167

upvoted a collection 5 months ago

V-JEPA 2

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 • 200