🏗️ Building on HF

Gökdeniz Gülmez PRO

Goekdeniz-Guelmez

·

https://gg-portfolio-2026.netlify.app

AI & ML interests

Transformers / NLP / Multimodal / Realtime M2M / J.O.S.I.E.-Home

Recent Activity

liked a dataset about 12 hours ago

r0b0tlab/qwen3.8-max-distillation-50k

liked a model about 12 hours ago

MiniMaxAI/MiniMax-H3

liked a model about 12 hours ago

deepseek-ai/DeepSeek-V4-Flash-0731

View all activity

Organizations

upvoted a collection 3 days ago

J.O.S.I.E-2

The new J.O.S.I.E. version 2 family of personality-driven language models trained entirely on Apple Silicon • 22 items • Updated about 15 hours ago • 9

upvoted a collection 9 days ago

Apertus v1.5

Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 2 items • Updated 2 days ago • 27

upvoted a changelog 13 days ago

Hugging Face Changelog

Egress metrics for users and organizations

14 days ago

• 97

upvoted a collection 2 months ago

Qwen 3.x MTP

MLX MTP drafter checkpoints for Qwen 3.x speculative decoding with mlx-vlm. • 12 items • Updated Jun 1 • 9

upvoted a paper 3 months ago

It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

Paper • 2602.12147 • Published Mar 4 • 4

upvoted a changelog 4 months ago

Hugging Face Changelog

Introducing Kernels

Apr 15

• 206

upvoted 3 articles 4 months ago

Article

Continuous batching from first principles

+1

ror, ArthurZ, mcpotato

•

Nov 25, 2025

• 427

Article

The PR you would have opened yourself

pcuenq, awni

•

Apr 16

• 72

Article

Welcome Gemma 4: Frontier multimodal intelligence on device

+5

merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift

•

Apr 2

• 918

upvoted a collection 4 months ago

Gemma 4

88 items • Updated Jun 3 • 147

upvoted a paper 4 months ago

daVinci-LLM:Towards the Science of Pretraining

Paper • 2603.27164 • Published Mar 28 • 32

upvoted 3 changelogs 4 months ago

Hugging Face Changelog

Introducing hf-mount

Mar 24

• 228

Hugging Face Changelog

Protected Spaces with Public URLs

Mar 20

• 130

Hugging Face Changelog

Hugging Face Papers for AI Agents

Mar 18

• 146

upvoted a changelog 5 months ago

Hugging Face Changelog

Repositories Usage Overview in Settings

Mar 18

• 60

upvoted a collection 5 months ago

JOSIE-1.1

The JOSIE-1.1 are the next iteration model family of uncensored, high-performance language models developed by Gökdeniz Gülmez. • 14 items • Updated about 15 hours ago • 2

upvoted a paper 5 months ago

DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks

Paper • 2603.01697 • Published Mar 2 • 2

upvoted a collection 5 months ago

JOSIE-MoE

JOSIE models using a custom dynamic Mixture of Expert architecture. • 1 item • Updated about 15 hours ago • 2

upvoted an article 5 months ago

Article

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

+4

ggerganov, ngxson, allozaur, lysandre, victor, julien-c

•

Feb 20

• 509

upvoted a collection 6 months ago

Tiny Aya

Bridging Scale and Multilingual Depth • 10 items • Updated Feb 17 • 77