Zeyu Qin's picture

21 19

Zeyu Qin

qqqzzzyyy

·

https://alan-qin.github.io/

Alan-Qin

AI & ML interests

Trustworthy ML, AI safety

Organizations

None yet

qqqzzzyyy's activity

upvoted a paper about 12 hours ago

Iterative Reasoning Preference Optimization

Paper • 2404.19733 • Published Apr 30 • 46

upvoted an article 13 days ago

Article

Let's talk about LLM evaluation

By

•

May 23

• 102

upvoted an article about 1 month ago

Article

SmolLM - blazingly fast and remarkably powerful

Jul 16

• 234

upvoted 4 collections about 2 months ago

Qwen1.5

Qwen1.5 is the improved version of Qwen, the large language model series developed by Alibaba Cloud. • 55 items • Updated Jun 6 • 206

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 35 items • Updated 22 days ago • 299

Coding Instruction datasets

4 items • Updated 18 days ago • 1

Awesome SFT datasets

A curated list of interesting datasets to fine-tune language models with. • 43 items • Updated Apr 12 • 110

upvoted a paper 2 months ago

Adam-mini: Use Fewer Learning Rates To Gain More

Paper • 2406.16793 • Published Jun 24 • 66

upvoted a paper 4 months ago

AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Paper • 2404.16873 • Published Apr 21 • 28

upvoted 2 papers 5 months ago

Localizing Paragraph Memorization in Language Models

Paper • 2403.19851 • Published Mar 28 • 13

Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression

Paper • 2403.15447 • Published Mar 18 • 15

upvoted a collection 5 months ago

Handbook v0.1 models and datasets

Models and datasets for v0.1 of the alignment handbook • 6 items • Updated Nov 10, 2023 • 23

upvoted a paper 5 months ago

Towards Optimal Learning of Language Models

Paper • 2402.17759 • Published Feb 27 • 16

upvoted 3 papers 6 months ago

Beyond Training Objectives: Interpreting Reward Model Divergence in Large Language Models

Paper • 2310.08164 • Published Oct 12, 2023 • 4

Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping

Paper • 2402.07610 • Published Feb 12 • 7

WARM: On the Benefits of Weight Averaged Reward Models

Paper • 2401.12187 • Published Jan 22 • 17

upvoted a collection 7 months ago

Model Merging

Model Merging is a very popular technique nowadays in LLM. Here is a chronological list of papers on the space that will help you get started with it! • 30 items • Updated Jun 12 • 207

upvoted 2 collections 8 months ago

RL/Alignment

197 items • Updated Jun 18 • 20

Journal Club

Candidate papers to read in the H4 journal club • 54 items • Updated Apr 21 • 25

upvoted a paper 9 months ago

SelfEval: Leveraging the discriminative nature of generative models for evaluation

Paper • 2311.10708 • Published Nov 17, 2023 • 14

upvoted a paper 10 months ago

Detecting Pretraining Data from Large Language Models

Paper • 2310.16789 • Published Oct 25, 2023 • 10