Heegyu Kim's picture

Heegyu Kim PRO

heegyu

·

https://github.com/HeegyuKim

HeegyuKim

AI & ML interests

NLP

Organizations

heegyu's activity

upvoted a collection 3 days ago

Cosmos Tokenizer

A suite of image and video tokenizers • 10 items • Updated 4 days ago • 12

upvoted a collection 15 days ago

Granite 3.0 Language Models

A series of language models trained by IBM licensed under Apache 2.0 license. We release both the base pretrained and instruct models. • 8 items • Updated 6 days ago • 86

upvoted a collection 22 days ago

Arch-Function

6 items • Updated 12 days ago • 7

upvoted 3 collections 23 days ago

LLM Safety Datasets

Korean safety, ethics dataset • 9 items • Updated Aug 7 • 2

En Ko Translate

영어 데이터셋을 한글로 번역한 데이터셋입니다. • 4 items • Updated 4 days ago • 1

Magpie Conversation Ko

Magpie 데이터셋 한국어 번역본 (@nayohan님 번역 모델 사용) • 10 items • Updated 4 days ago • 1

upvoted a paper 27 days ago

MixEval: Deriving Wisdom of the Crowd from LLM Benchmark Mixtures

Paper • 2406.06565 • Published Jun 3 • 9

upvoted a collection 2 months ago

3D

Stability AI's suite of models for 3D generation • 5 items • Updated Aug 9 • 29

upvoted 2 collections 3 months ago

4bit Instruct Models

18 items • Updated 28 days ago • 25

DeepSeek-Prover

DeepSeek-V1-and-V1.5-Series • 7 items • Updated Aug 16 • 17

upvoted 2 collections 4 months ago

Magpie-Qwen2 Datasets

Dataset built with Qwen2 72B and Qwen2 7B. • 6 items • Updated Sep 14 • 10

Awesome feedback datasets

A curated list of datasets with human or AI feedback. Useful for training reward models or applying techniques like DPO. • 19 items • Updated Apr 12 • 65

upvoted a collection 5 months ago

Standard-format-preference-dataset

We collect the open-source datasets and process them into the standard format. • 14 items • Updated May 8 • 21

upvoted a paper 6 months ago

DoRA: Weight-Decomposed Low-Rank Adaptation

Paper • 2402.09353 • Published Feb 14 • 26

upvoted a collection 7 months ago

Eurus

Advancing LLM Reasoning Generalists with Preference Trees • 11 items • Updated 19 days ago • 24

upvoted 2 papers 8 months ago

Shepherd: A Critic for Language Model Generation

Paper • 2308.04592 • Published Aug 8, 2023 • 29

PERL: Parameter Efficient Reinforcement Learning from Human Feedback

Paper • 2403.10704 • Published Mar 15 • 57

upvoted a collection 8 months ago

zephyr-7b-sft-full-SPIN

Models fine-tuned with SPIN across iterations 0,1,2,3 • 4 items • Updated Feb 7 • 8

upvoted a paper 8 months ago

Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning

Paper • 2402.06619 • Published Feb 9 • 54

upvoted a collection 8 months ago

Multilingual

128 items • Updated Jul 24 • 10