Kayky Ramos

kaykyramos

kaykyr

AI & ML interests

Artificial General Intelligence, Small Models Capabilities Improvements, Small Models Reasoning Improvements, Multimodal Models, Consumer-Grade GPUs, Preference alignment, Supervised fine-tuning

Recent Activity

liked a dataset 5 days ago

orion-research/Reflective-MAGLLAMA-Filtered-v0.1

View all activity

Organizations

kaykyramos's activity

upvoted a collection 8 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 16 days ago • 695

upvoted an article 8 months ago

Article

Create Mixtures of Experts with MergeKit

•

Mar 28

• 12

upvoted a collection 9 months ago

ChatGPT-Mini

Collection

A collection of fine-tuned GPT-2 models each designed to deploy a ChatGPT-like model at home. These models can also be deployed on an old computer. • 8 items • Updated Nov 16, 2023 • 5

upvoted a paper 9 months ago

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Paper • 2403.09629 • Published Mar 14 • 74