danielpark (Minwoo Park)

upvoted a collection 23 days ago

Preference Datasets for DPO

This collection contains a list of curated preference datasets for DPO fine-tuning for intent alignment of LLMs • 7 items • Updated Apr 4 • 19

upvoted an article 23 days ago

Article

Can We Train Chat Models with Raw Data?

By

•

24 days ago

• 17

upvoted an article 25 days ago

Article

Fine-tune Llama 2 with DPO

Aug 8, 2023

• 11

upvoted an article about 1 month ago

Article

CodeGemma - an official Google release for code LLMs

Apr 9

• 95

upvoted a collection about 1 month ago

Korean-Adapted Model Series

Collection

Korean-adapted Language Model Series • 13 items • Updated 2 days ago • 15

upvoted 4 papers about 2 months ago

MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection

Paper • 2403.19888 • Published Mar 29 • 9

YaRN: Efficient Context Window Extension of Large Language Models

Paper • 2309.00071 • Published Aug 31, 2023 • 57

The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI

Paper • 2310.16787 • Published Oct 25, 2023 • 3

sDPO: Don't Use Your Data All at Once

Paper • 2403.19270 • Published Mar 28 • 31

upvoted a collection 3 months ago

Sora Reference Papers

Collection

A collection of all papers referenced in OpenAI's "Video generation models as world simulators" technical report • openai.com/sora • 30 items • Updated Feb 20 • 50

upvoted a collection 7 months ago

Zephyr 7B

Collection

Models, datasets, and demos associated with Zephyr 7B. For code to train the models, see: https://github.com/huggingface/alignment-handbook • 9 items • Updated Apr 12 • 137

upvoted 4 papers 9 months ago

upvoted a paper 10 months ago

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Paper • 2306.02707 • Published Jun 5, 2023 • 45

Minwoo Park

AI & ML interests

Organizations

danielpark's activity

Preference Datasets for DPO

Can We Train Chat Models with Raw Data?

Fine-tune Llama 2 with DPO

CodeGemma - an official Google release for code LLMs

Korean-Adapted Model Series

MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection

YaRN: Efficient Context Window Extension of Large Language Models

The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI

sDPO: Don't Use Your Data All at Once

Sora Reference Papers

Zephyr 7B

Hardwiring ViT Patch Selectivity into CNNs using Patch Mixing

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Platypus: Quick, Cheap, and Powerful Refinement of LLMs

Self-Alignment with Instruction Backtranslation

Orca: Progressive Learning from Complex Explanation Traces of GPT-4