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 dataset about 15 hours ago

agibot-world/AgiBotWorld-Alpha

liked a dataset 1 day ago

johannhartmann/orpo-dpo-mix-40k-llama3-de

liked a dataset 1 day ago

mayflowergmbh/distilabel-math-preference-dpo-de

View all activity

Organizations

Goekdeniz-Guelmez's activity

upvoted an article 8 days ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 230

upvoted a collection 15 days ago

Falcon3 Mamba

3 items • Updated 15 days ago • 1

upvoted a collection 17 days ago

Josiefied

The best uncensored models • 16 items • Updated 17 days ago • 1

upvoted a collection 20 days ago

Llama 3.2

Meta goes small with Llama3.2, both text only 1B and 3B, and the 11B Vision models. • 15 items • Updated 20 days ago • 10

upvoted a collection about 1 month ago

Molmo

4 items • Updated Nov 23, 2024 • 2

upvoted 2 papers about 2 months ago

Both Text and Images Leaked! A Systematic Analysis of Multimodal LLM Data Contamination

Paper • 2411.03823 • Published Nov 6, 2024 • 43

Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level

Paper • 2411.03562 • Published Nov 5, 2024 • 64

upvoted a collection 2 months ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated 14 days ago • 197

upvoted a paper 2 months ago

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25, 2024 • 75

upvoted an article 2 months ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

Oct 27, 2024

• 37

upvoted 5 collections 3 months ago

Papers - MoE

46 items • Updated 15 days ago • 3

Josiefied and Abliterated

Abliterated, and further fine-tuned to be the most uncensored models available. • 13 items • Updated 17 days ago • 4

🍷 FineWeb datasets

5 items • Updated Jun 26, 2024 • 22

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Nov 27, 2024 • 291

Llama 3.2

Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. • 23 items • Updated 12 days ago • 46

upvoted a paper 3 months ago

Kolmogorov-Arnold Transformer

Paper • 2409.10594 • Published Sep 16, 2024 • 39

upvoted 2 collections 4 months ago

Mamba

Mamba is a new LLM architecture that integrates the Structured State Space sequence model to manage lengthy data sequences. • 11 items • Updated Oct 12, 2024 • 1

Transformers compatible Mamba

This release includes the `mamba` repositories compatible with the `transformers` library • 5 items • Updated Mar 6, 2024 • 37

upvoted 2 articles 4 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13, 2024

• 388

Article

Recreating o1 at Home with Role-Play LLMs

By

•

Sep 20, 2024

• 23