Gmc2 (Maozhou Ge)

upvoted a paper 2 days ago

MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression

Paper • 2406.14909 • Published 10 days ago • 12

upvoted a collection 3 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 4 days ago • 121

upvoted a paper 3 days ago

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published 7 days ago • 56

upvoted a paper 4 days ago

A Closer Look into Mixture-of-Experts in Large Language Models

Paper • 2406.18219 • Published 5 days ago • 12

upvoted a paper 5 days ago

Unlocking Continual Learning Abilities in Language Models

Paper • 2406.17245 • Published 6 days ago • 26

upvoted 2 papers 6 days ago

Long Context Transfer from Language to Vision

Paper • 2406.16852 • Published 7 days ago • 30

Scaling Laws for Linear Complexity Language Models

Paper • 2406.16690 • Published 7 days ago • 21

upvoted a paper 14 days ago

Needle In A Multimodal Haystack

Paper • 2406.07230 • Published 20 days ago • 51

upvoted a paper 16 days ago

Language Modeling Is Compression

Paper • 2309.10668 • Published Sep 19, 2023 • 81

upvoted 2 papers 19 days ago

Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models

Paper • 2406.06563 • Published 28 days ago • 17

An Image is Worth 32 Tokens for Reconstruction and Generation

Paper • 2406.07550 • Published 20 days ago • 53

upvoted a paper 25 days ago

Training-Free Long-Context Scaling of Large Language Models

Paper • 2402.17463 • Published Feb 27 • 19

upvoted 7 papers about 1 month ago

upvoted 2 papers about 2 months ago

A Unified Sequence Parallelism Approach for Long Context Generative AI

Paper • 2405.07719 • Published May 13 • 1

Beyond Scaling Laws: Understanding Transformer Performance with Associative Memory

Paper • 2405.08707 • Published May 14 • 27

upvoted 2 articles about 2 months ago

Article

Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face

Dec 11, 2023

• 8

Article

Mixture of Experts Explained

Dec 11, 2023

• 99

upvoted 4 papers about 2 months ago

Generating Long Sequences with Sparse Transformers

Paper • 1904.10509 • Published Apr 23, 2019 • 1

Longformer: The Long-Document Transformer

Paper • 2004.05150 • Published Apr 10, 2020 • 3

vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention

Paper • 2405.04437 • Published May 7 • 3

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

Paper • 2306.12929 • Published Jun 22, 2023 • 11

upvoted 2 papers 2 months ago

Make Your LLM Fully Utilize the Context

Paper • 2404.16811 • Published Apr 25 • 52

OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework

Paper • 2404.14619 • Published Apr 22 • 124

upvoted a collection 2 months ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Apr 18 • 616

upvoted 2 papers 3 months ago

Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length

Paper • 2404.08801 • Published Apr 12 • 62

Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Paper • 2404.07143 • Published Apr 10 • 97

upvoted an article 3 months ago

Article

Llama 2 is here - get it on Hugging Face

Jul 18, 2023

• 17

upvoted a paper 3 months ago

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies

Paper • 2404.06395 • Published Apr 9 • 18

upvoted an article 3 months ago

Article

The Technology Behind BLOOM Training

Jul 14, 2022

• 5

upvoted 10 papers 3 months ago

Octopus v2: On-device language model for super agent

Paper • 2404.01744 • Published Apr 2 • 55

MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens

Paper • 2404.03413 • Published Apr 4 • 22

Long-context LLMs Struggle with Long In-context Learning

Paper • 2404.02060 • Published Apr 2 • 33

Mixture-of-Depths: Dynamically allocating compute in transformer-based language models

Paper • 2404.02258 • Published Apr 2 • 102

Rethinking Memory and Communication Cost for Efficient Large Language Model Training

Paper • 2310.06003 • Published Oct 9, 2023 • 2

Optimized Network Architectures for Large Language Model Training with Billions of Parameters

Paper • 2307.12169 • Published Jul 22, 2023 • 9

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 154

Cobra: Extending Mamba to Multi-Modal Large Language Model for Efficient Inference

Paper • 2403.14520 • Published Mar 21 • 31

Unicron: Economizing Self-Healing LLM Training at Scale

Paper • 2401.00134 • Published Dec 30, 2023 • 9

LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens

Paper • 2402.13753 • Published Feb 21 • 106

upvoted 7 papers 4 months ago

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

Paper • 2403.09919 • Published Mar 14 • 19

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Paper • 2401.01325 • Published Jan 2 • 25

Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey

Paper • 2311.12351 • Published Nov 21, 2023 • 3

Infinite-LLM: Efficient LLM Service for Long Context with DistAttention and Distributed KVCache

Paper • 2401.02669 • Published Jan 5 • 12

Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models

Paper • 2402.02244 • Published Feb 3 • 1

BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences

Paper • 2403.09347 • Published Mar 14 • 20

LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

Paper • 2310.03294 • Published Oct 5, 2023 • 2

upvoted a collection 4 months ago

Long context

Collection

80 items • Updated 13 days ago • 24

upvoted 7 papers 4 months ago

DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Paper • 2309.14509 • Published Sep 25, 2023 • 16

Striped Attention: Faster Ring Attention for Causal Transformers

Paper • 2311.09431 • Published Nov 15, 2023 • 4

Ring Attention with Blockwise Transformers for Near-Infinite Context

Paper • 2310.01889 • Published Oct 3, 2023 • 9

Sequence Parallelism: Long Sequence Training from System Perspective

Paper • 2105.13120 • Published May 26, 2021 • 5

Algorithmic progress in language models

Paper • 2403.05812 • Published Mar 9 • 17

DeepSeek-VL: Towards Real-World Vision-Language Understanding

Paper • 2403.05525 • Published Mar 8 • 39

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Paper • 2403.05530 • Published Mar 8 • 51

Maozhou Ge

AI & ML interests

Organizations

Gmc2's activity

Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face

Mixture of Experts Explained

Llama 2 is here - get it on Hugging Face

The Technology Behind BLOOM Training