Jiwoo Hong's picture

Jiwoo Hong

JW17

·

https://jiwooya1000.github.io/

AI & ML interests

NLP, LLM, and any related topics

Recent Activity

upvoted a paper 3 days ago

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

updated a model 13 days ago

reasoning-project/Q25M-1.5B-MR1-50k-SFT-v0.2-3epoch

published a model 13 days ago

reasoning-project/Q25M-1.5B-MR1-50k-SFT-v0.2-3epoch

View all activity

Organizations

JW17's activity

upvoted a paper 3 days ago

Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning

Paper • 2502.17407 • Published 4 days ago • 22

upvoted a collection 5 months ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 46 items • Updated 2 days ago • 535

upvoted an article 6 months ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16, 2024

• 323

upvoted an article 8 months ago

Article

Putting RL back in RLHF

Jun 12, 2024

• 77

upvoted a paper 9 months ago

Margin-aware Preference Optimization for Aligning Diffusion Models without Reference

Paper • 2406.06424 • Published Jun 10, 2024 • 13

upvoted a collection 9 months ago

MaPO

This collection includes the models and datasets as a part of the MaPO release. • 9 items • Updated Jun 12, 2024 • 5

upvoted a paper 9 months ago

Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets

Paper • 2405.18952 • Published May 29, 2024 • 10

upvoted an article 10 months ago

Article

How to Finetune phi-3 on MacBook Pro

By

•

Apr 24, 2024

• 66

upvoted an article 11 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 233

upvoted 2 collections 11 months ago

Meta Llama 3

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Dec 6, 2024 • 714

Zephyr ORPO

Models and datasets to align LLMs with Odds Ratio Preference Optimisation (ORPO). Recipes here: https://github.com/huggingface/alignment-handbook • 3 items • Updated Apr 12, 2024 • 17

upvoted a paper 11 months ago

ORPO: Monolithic Preference Optimization without Reference Model

Paper • 2403.07691 • Published Mar 12, 2024 • 64

upvoted a collection 11 months ago

ORPO

This is the official collection of "ORPO: Monolithic Preference Optimization without Reference Model". • 5 items • Updated Apr 12, 2024 • 11