Slach (Eugene Klimov)

upvoted 2 collections 4 days ago

AQLM

Collection

AQLM quantized LLMs • 20 items • Updated May 3 • 33

AQLM+PV

Collection

14 items • Updated about 11 hours ago • 8

upvoted a collection 6 days ago

NuminaMath

Collection

Datasets and models for training SOTA math LLMs. See our GitHub for training & inference code: https://github.com/project-numina/aimo-progress-prize • 6 items • Updated 6 days ago • 45

upvoted a paper 18 days ago

Associative Recurrent Memory Transformer

Paper • 2407.04841 • Published 22 days ago • 31

upvoted a paper 2 months ago

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19 • 147

upvoted a collection 3 months ago

Edit Your Image!

Collection

Find all the trending and useful Gradio demos that you can use to edit your images. • 21 items • Updated Apr 26 • 23

upvoted a paper 4 months ago

OmniFusion Technical Report

Paper • 2404.06212 • Published Apr 9 • 72

upvoted a paper 6 months ago

MambaByte: Token-free Selective State Space Model

Paper • 2401.13660 • Published Jan 24 • 47

upvoted a collection 6 months ago

vikhr

Collection

A family of russian translated LLM • 4 items • Updated Jan 8 • 14

upvoted a paper 8 months ago

DiLoCo: Distributed Low-Communication Training of Language Models

Paper • 2311.08105 • Published Nov 14, 2023 • 14

upvoted a paper 9 months ago

Prompt Cache: Modular Attention Reuse for Low-Latency Inference

Paper • 2311.04934 • Published Nov 7, 2023 • 26

upvoted a paper about 1 year ago

AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn

Paper • 2306.08640 • Published Jun 14, 2023 • 26

Eugene Klimov

AI & ML interests

Organizations

Slach's activity

AQLM

AQLM+PV

NuminaMath

Associative Recurrent Memory Transformer

Your Transformer is Secretly Linear

Edit Your Image!

OmniFusion Technical Report

MambaByte: Token-free Selective State Space Model

vikhr

DiLoCo: Distributed Low-Communication Training of Language Models

Prompt Cache: Modular Attention Reuse for Low-Latency Inference

AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn