liminalism (Lim)

upvoted a paper about 1 month ago

Better & Faster Large Language Models via Multi-token Prediction

Paper • 2404.19737 • Published Apr 30 • 64

upvoted 2 papers about 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 • 123

upvoted a collection about 2 months ago

OpenELM Instruct Models

Collection

4 items • Updated 2 days ago • 102

upvoted a paper about 2 months ago

FlowMind: Automatic Workflow Generation with LLMs

Paper • 2404.13050 • Published Mar 17 • 32

upvoted 2 papers 2 months ago

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Paper • 2404.05961 • Published Apr 9 • 62

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

Paper • 2403.05313 • Published Mar 8 • 9

upvoted an article 2 months ago

Article

CodeGemma - an official Google release for code LLMs

Apr 9

• 97

upvoted a paper 2 months ago

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4 • 74

upvoted 2 collections 2 months ago

🤖 Agents

Collection

16 items • Updated Apr 24 • 20

MoEs papers reading list

Collection

44 items • Updated 3 days ago • 126

upvoted 3 papers 3 months ago

upvoted a paper 5 months ago

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 154

upvoted a paper 6 months ago

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 255

Lim

AI & ML interests

Organizations

liminalism's activity

Better & Faster Large Language Models via Multi-token Prediction

Make Your LLM Fully Utilize the Context

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

OpenELM Instruct Models

FlowMind: Automatic Workflow Generation with LLMs

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

CodeGemma - an official Google release for code LLMs

ReFT: Representation Finetuning for Language Models

🤖 Agents

MoEs papers reading list

Jamba: A Hybrid Transformer-Mamba Language Model

LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Mixtral of Experts

LLM in a flash: Efficient Large Language Model Inference with Limited Memory