Gökdeniz Gülmez's picture

Gökdeniz Gülmez

Goekdeniz-Guelmez

·

AI & ML interests

Transformers / NLP / Multimodal / Realtime M2M / J.O.S.I.E.v4o

Recent Activity

liked a model 1 day ago

google/gemma-3-4b-it

liked a model 1 day ago

google/gemma-3-12b-it

upvoted a collection 1 day ago

Gemma 3 Release

View all activity

Organizations

Goekdeniz-Guelmez's activity

upvoted a collection 1 day ago

Gemma 3 Release

9 items • Updated about 3 hours ago • 217

upvoted a collection 9 days ago

C4AI Aya Vision

Aya Vision is a state-of-the-art family of vision models that brings multimodal capabilities to 23 languages. • 5 items • Updated 9 days ago • 63

upvoted a collection 13 days ago

Kokoro TTS

Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers amazing quality. • 4 items • Updated 13 days ago • 2

upvoted a collection 24 days ago

Nomic Embed v2

Multilingual Embedding Models • 4 items • Updated 26 days ago • 16

upvoted a paper 24 days ago

Hermes 3 Technical Report

Paper • 2408.11857 • Published Aug 15, 2024 • 48

upvoted a collection 24 days ago

Hermes 3

The Hermes 3 Series of Models • 12 items • Updated 28 days ago • 112

upvoted a collection about 1 month ago

Granite Experiments

Experimental projects under consideration for the Granite family. • 6 items • Updated 15 days ago • 9

upvoted 2 articles about 1 month ago

Article

Welcome to Inference Providers on the Hub 🔥

Jan 28

• 429

Article

Proximal Policy Optimization (PPO)

Aug 5, 2022

• 25

upvoted 3 collections about 1 month ago

DolphinLabeled Datasets

Eric Hartford has added labels to help you filter datasets, for your pleasure. • 5 items • Updated Jan 6 • 14

Qwen2.5-VL

18 items • Updated 19 days ago • 4

Qwen2.5-1M

10 items • Updated Jan 26 • 5

upvoted 3 collections about 2 months ago

Qwen2.5-VL

Vision-language model series based on Qwen2.5 • 8 items • Updated 18 days ago • 396

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 3 items • Updated 16 days ago • 106

Helium-1

Kyutai's Helium-1 2B Model, outperforming other state of the art small models. • 4 items • Updated Jan 18 • 1

upvoted 4 collections 2 months ago

J.O.S.I.E. v6.0

Trained on opensourced and private custom DPO/ORPO datasets • 8 items • Updated Feb 7 • 2

KaLM-embedding

11 items • Updated 3 days ago • 23

QVQ-72B-Preview

5 items • Updated Dec 24, 2024 • 7

Dolphin 3.0

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 9 items • Updated Feb 7 • 107

upvoted an article 2 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 234