Zach Mustafa's picture

Zach Mustafa PRO

Zmu

·

AI & ML interests

None yet

Recent Activity

upvoted a collection about 14 hours ago

liked a Space 2 days ago

Qwen/Qwen3.5-Omni-Offline-Demo

liked a model 2 days ago

Qwen/Qwen3.5-9B

View all activity

Organizations

upvoted a collection about 14 hours ago

Bonsai

1-bit Bonsai models • 6 items • Updated 1 day ago • 107

upvoted 3 changelogs 2 days ago

Hugging Face Changelog

Community Evals and Benchmark Repositories

Feb 5

• 76

Hugging Face Changelog

Hugging Face Papers for AI Agents

15 days ago

• 129

Hugging Face Changelog

Introducing hf-mount

9 days ago

• 202

upvoted 3 articles 2 days ago

Article

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

+2

28 days ago

•

47

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+7

23 days ago

•

90

Article

A New Framework for Evaluating Voice Agents (EVA)

9 days ago

•

81

upvoted an article 7 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 8 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 8 days ago

AutoGaze

7 items • Updated 13 days ago • 9

upvoted an article 15 days ago

Article

State of Open Source on Hugging Face: Spring 2026

16 days ago

•

76

upvoted an article about 1 month 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 24 days ago • 1.39k

upvoted an article about 2 months ago

Article

NVIDIA brings agents to life with DGX Spark and Reachy Mini

+1

Jan 5

•

66

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. • 110 items • Updated about 5 hours ago • 50

✂️ Abliteration

Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration • 32 items • Updated about 1 month ago • 164

Qwen3-VL-abliterated

14 items • Updated about 1 month ago • 32

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 about 1 month ago • 220

Qwen3-TTS

7 items • Updated Jan 22 • 339