Seungwoo Ryu's picture

Seungwoo Ryu PRO

tryumanshow

·

tryumanshow

AI & ML interests

LLM, Multimodal, Agent

Organizations

tryumanshow's activity

upvoted a collection 18 days ago

Korean Reward Modeling

Korean Datasets, Reward Models for RLHF • 16 items • Updated May 29 • 3

upvoted a paper 27 days ago

DiaSynth -- Synthetic Dialogue Generation Framework

Paper • 2409.19020 • Published Sep 25 • 19

upvoted an article about 2 months ago

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22

• 85

upvoted a collection 2 months ago

LLMs

266 items • Updated about 12 hours ago • 16

upvoted 2 papers 4 months ago

Octo-planner: On-device Language Model for Planner-Action Agents

Paper • 2406.18082 • Published Jun 26 • 47

Model Merging and Safety Alignment: One Bad Model Spoils the Bunch

Paper • 2406.14563 • Published Jun 20 • 29

upvoted 2 collections 5 months ago

Function Calling v3

Models fine-tuned for function-calling • 14 items • Updated Apr 27 • 19

Agents

Collection of resources related to Agents. • 67 items • Updated 1 day ago • 4

upvoted 2 collections 6 months ago

Miqu Models ('slerp' + 'model_stock')

A collection of creative writing models based on the 'miqu-1-70b ' model. • 9 items • Updated 4 days ago • 2

Agents

61 items • Updated 17 days ago • 5

upvoted a paper 6 months ago

Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

Paper • 2405.00664 • Published May 1 • 18

upvoted an article 6 months ago

Article

Mixture of Experts Explained

Dec 11, 2023

• 174

upvoted a collection 6 months ago

Long context

94 items • Updated 30 days ago • 29

upvoted an article 6 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22

• 223

upvoted a collection 6 months ago

Handbook v0.1 models and datasets

Models and datasets for v0.1 of the alignment handbook • 6 items • Updated Nov 10, 2023 • 24