Gökdeniz Gülmez (Isaak Carter Augustus)'s picture

Gökdeniz Gülmez (Isaak Carter Augustus)

Goekdeniz-Guelmez

·

AI & ML interests

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

Organizations

Goekdeniz-Guelmez's activity

upvoted 2 papers 4 days ago

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

Paper • 2411.03823 • Published 6 days ago • 41

Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level

Paper • 2411.03562 • Published 6 days ago • 47

upvoted a collection 7 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 7 days ago • 163

upvoted a paper 12 days ago

LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25 • 73

upvoted an article 15 days ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

15 days ago

• 37

upvoted 2 collections 21 days ago

Papers - MoE

45 items • Updated Aug 23 • 3

Josiefied and Abliterated

Abliterated, and further fine-tuned to be the most uncensored models available. • 7 items • Updated 17 days ago • 3

upvoted a collection about 1 month ago

🍷 FineWeb datasets

5 items • Updated Jun 26 • 19

upvoted 2 collections about 2 months ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Sep 26 • 269

Llama 3.2 All Versions

Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. • 20 items • Updated Oct 6 • 36

upvoted a paper about 2 months ago

Kolmogorov-Arnold Transformer

Paper • 2409.10594 • Published Sep 16 • 38

upvoted 2 collections about 2 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 about 1 month ago • 1

Transformers compatible Mamba

This release includes the `mamba` repositories compatible with the `transformers` library • 5 items • Updated Mar 6 • 36

upvoted 2 articles about 2 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 364

Article

Recreating o1 at Home with Role-Play LLMs

By

•

Sep 20

• 20

upvoted 3 collections about 2 months ago

Qwen2.5

The Qwen 2.5 models are a series of AI models trained on 18 trillion tokens, supporting 29 languages and offering advanced features such as instructio • 33 items • Updated about 1 month ago • 4

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated Sep 18 • 318

Moshi v0.1 Release

MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi • 13 items • Updated Sep 18 • 215

upvoted 2 articles 3 months ago

Article

What is Retrieval-based Voice Conversion WebUI?

By

•

Aug 18

• 9

Article

Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth

By

•

Jul 29

• 238