tryumanshow (Seungwoo Ryu)

upvoted a paper 30 days ago

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

Paper • 2411.16489 • Published Nov 25, 2024 • 46

upvoted an article about 2 months ago

Article

Fixing Gradient Accumulation

Oct 16, 2024

• 51

upvoted a collection 4 months ago

Korean Instruction Dataset

Collection

5 items • Updated Jan 24 • 7

upvoted 2 collections 5 months ago

MobileLLM

Collection

Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905 • 9 items • Updated Nov 27, 2024 • 111

Korean Reward Modeling

Collection

Korean Datasets, Reward Models for RLHF • 16 items • Updated Nov 19, 2024 • 3

upvoted a paper 6 months ago

DiaSynth -- Synthetic Dialogue Generation Framework

Paper • 2409.19020 • Published Sep 25, 2024 • 21

upvoted an article 6 months ago

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22, 2024

• 87

upvoted a collection 7 months ago

LLMs

Collection

418 items • Updated 3 days ago • 31

upvoted 2 papers 9 months ago

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

Paper • 2406.18082 • Published Jun 26, 2024 • 48

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

Paper • 2406.14563 • Published Jun 20, 2024 • 30

upvoted 4 collections 10 months ago

upvoted a paper 10 months ago

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

Paper • 2405.00664 • Published May 1, 2024 • 20

upvoted an article 10 months ago

Article

Mixture of Experts Explained

Dec 11, 2023

• 459

upvoted a collection 11 months ago

Long context

Collection

94 items • Updated Sep 29, 2024 • 31

upvoted an article 11 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 235

upvoted a collection 11 months ago

Handbook v0.1 models and datasets

Collection

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

Seungwoo Ryu PRO

AI & ML interests

Organizations

tryumanshow's activity

O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?

Fixing Gradient Accumulation

Korean Instruction Dataset

MobileLLM

Korean Reward Modeling

DiaSynth -- Synthetic Dialogue Generation Framework

The 5 Most Under-Rated Tools on Hugging Face

LLMs

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

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

Function Calling v3

Agents

Miqu-based Models

Agents

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

Mixture of Experts Explained

Long context

Fine-tune Llama 3 with ORPO

Handbook v0.1 models and datasets