GPT007 (Marc Kovka)

upvoted a collection 3 days ago

DynMoE Family

Collection

DynMoE model checkpoints and paper on huggingface • 4 items • Updated 3 days ago • 3

upvoted a paper 4 days ago

Scaling Diffusion Transformers to 16 Billion Parameters

Paper • 2407.11633 • Published 6 days ago • 21

upvoted a collection 6 days ago

DCLM

Collection

DCLM Models + Datasets • 6 items • Updated 4 days ago • 16

upvoted a paper 7 days ago

Training language models to follow instructions with human feedback

Paper • 2203.02155 • Published Mar 4, 2022 • 13

upvoted a collection 8 days ago

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 29 items • Updated Jun 6 • 260

upvoted a paper 8 days ago

Video Diffusion Alignment via Reward Gradients

Paper • 2407.08737 • Published 11 days ago • 41

upvoted an article 10 days ago

Article

Introducing Ghost 8B Beta: A Game-Changing Language Model

By

•

5 days ago

• 6

upvoted a paper 11 days ago

Self-Rewarding Language Models

Paper • 2401.10020 • Published Jan 18 • 138

upvoted an article 11 days ago

Article

Train a Llama model from scratch

By

•

about 19 hours ago

• 24

upvoted 2 papers 11 days ago

Vision language models are blind

Paper • 2407.06581 • Published 13 days ago • 73

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

Paper • 2407.06723 • Published 13 days ago • 9

upvoted an article 11 days ago

Article

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

By

•

12 days ago

• 9

upvoted a collection 15 days ago

Collection Zero

Collection

Image Gen - Text -to-Image • 21 items • Updated 2 days ago • 5

upvoted 2 collections 16 days ago

Most influential papers in AI

Collection

4 items • Updated Nov 16, 2023 • 27

Transformers.js demos

Collection

A collection of my favorite WebML demos, built with Transformers.js! • 30 items • Updated 11 days ago • 60

upvoted a paper 17 days ago

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Paper • 2407.02687 • Published 20 days ago • 20

upvoted a collection 17 days ago

Perturbed Attention Guidance pipelines

Collection

Pipelines for Perturbed Attention Guidance with 🧨 library • 8 items • Updated 26 days ago • 5

upvoted a collection 18 days ago

LLM Compiler

Collection

Meta LLM Compiler is a state-of-the-art LLM that builds upon Code Llama with improved performance for code optimization and compiler reasoning. • 4 items • Updated 25 days ago • 140

upvoted a collection 22 days ago

Gemma 2 Release

Collection

10 items • Updated 25 days ago • 129

upvoted 2 papers 23 days ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published 27 days ago • 75

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published 28 days ago • 65

upvoted a paper 24 days ago

MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data

Paper • 2406.18790 • Published 26 days ago • 32

upvoted a paper 27 days ago

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Paper • 2406.16855 • Published 28 days ago • 53

upvoted an article 27 days ago

Article

Introducing Würstchen: Fast Diffusion for Image Generation

Sep 13, 2023

• 8

upvoted 2 papers about 1 month ago

VideoTetris: Towards Compositional Text-to-Video Generation

Paper • 2406.04277 • Published Jun 6 • 21

TextGrad: Automatic "Differentiation" via Text

Paper • 2406.07496 • Published Jun 11 • 25

upvoted a collection about 1 month ago

abliterated-v3

Collection

Latest gen of the abliterated models I've produced • 17 items • Updated Jun 3 • 74

upvoted an article about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 238

upvoted 2 collections about 2 months ago

OpenMath

Collection

A collection of models and datasets introduced in "OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset" • 15 items • Updated 5 days ago • 32

🍷 FineWeb datasets

Collection

5 items • Updated 26 days ago • 15

upvoted a paper about 2 months ago

Attention Is All You Need

Paper • 1706.03762 • Published Jun 12, 2017 • 40

upvoted 3 collections about 2 months ago

upvoted a paper about 2 months ago

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1 • 25

upvoted an article 2 months ago

Article

Decoding GPT-4'o': In-Depth Exploration of Its Mechanisms and Creating Similar AI.

By

•

May 21

• 28

Marc Kovka

AI & ML interests

Organizations

GPT007's activity

DynMoE Family

Scaling Diffusion Transformers to 16 Billion Parameters

DCLM

Training language models to follow instructions with human feedback

Qwen2

Video Diffusion Alignment via Reward Gradients

Introducing Ghost 8B Beta: A Game-Changing Language Model

Self-Rewarding Language Models

Train a Llama model from scratch

Vision language models are blind

Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions

MInference 1.0: 10x Faster Million Context Inference with a Single GPU

Collection Zero

Most influential papers in AI

Transformers.js demos

No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models

Perturbed Attention Guidance pipelines

LLM Compiler

Gemma 2 Release

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Adam-mini: Use Fewer Learning Rates To Gain More

MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

Introducing Würstchen: Fast Diffusion for Image Generation

VideoTetris: Towards Compositional Text-to-Video Generation

TextGrad: Automatic "Differentiation" via Text

abliterated-v3

Uncensor any LLM with abliteration

OpenMath

🍷 FineWeb datasets

Attention Is All You Need

WizardLM

Universal token classification

Anime Diffusion

Executable Code Actions Elicit Better LLM Agents

Decoding GPT-4'o': In-Depth Exploration of Its Mechanisms and Creating Similar AI.