Michael Kingston's picture

25 4

Michael Kingston

michael-kingston

·

mkingopng

AI & ML interests

Transformers of course! :)

Recent Activity

upvoted an article 25 days ago

Better RAG 2: Single-shot is not good enough

upvoted an article 25 days ago

Better RAG 1: Advanced Basics

View all activity

Organizations

michael-kingston's activity

upvoted 2 articles 25 days ago

Article

Better RAG 2: Single-shot is not good enough

By

•

Mar 14

• 10

Article

Better RAG 1: Advanced Basics

By

•

Mar 14

• 19

upvoted an article 5 months ago

Article

Goodbye Python, Hello Rust: Building a RAG CLI Application with Orca

By

•

Nov 4, 2023

• 3

updated a model about 1 year ago

michael-kingston/ppo-Huggy

Reinforcement Learning • Updated Nov 7, 2023 • 16

liked a Space about 1 year ago

Huggy

updated 2 models about 1 year ago

michael-kingston/ppo-LunarLander-v2

Reinforcement Learning • Updated Oct 25, 2023 • 9

michael-kingston/ppo-LunarLander-v2-1

Reinforcement Learning • Updated Oct 25, 2023

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted a paper about 1 year ago

QLoRA: Efficient Finetuning of Quantized LLMs

Paper • 2305.14314 • Published May 23, 2023 • 46

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted a paper about 1 year ago

ChessGPT: Bridging Policy Learning and Language Modeling

Paper • 2306.09200 • Published Jun 15, 2023 • 9

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted a paper about 1 year ago

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Paper • 2307.02486 • Published Jul 5, 2023 • 80

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted a paper about 1 year ago

Secrets of RLHF in Large Language Models Part I: PPO

Paper • 2307.04964 • Published Jul 11, 2023 • 28

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted 2 papers about 1 year ago

Retentive Network: A Successor to Transformer for Large Language Models

Paper • 2307.08621 • Published Jul 17, 2023 • 170

How is ChatGPT's behavior changing over time?

Paper • 2307.09009 • Published Jul 18, 2023 • 23

updated a collection about 1 year ago

catchup readings

14 items • Updated Oct 20, 2023 • 1

upvoted a paper about 1 year ago

Llama 2: Open Foundation and Fine-Tuned Chat Models

Paper • 2307.09288 • Published Jul 18, 2023 • 242