Shuyu Wu's picture

2 3 16

Shuyu Wu

wonderwind271

·

https://shuyuwu.me

wonderwind271

AI & ML interests

LLM (pre)training dynamics; Mechanistic Interpretability

Recent Activity

liked a model about 1 hour ago

meta-llama/Llama-3.2-1B

updated a dataset about 20 hours ago

Seed42Lab/en-ud-train-pair

published a dataset about 20 hours ago

Seed42Lab/en-ud-train-pair

View all activity

Organizations

wonderwind271 's models 15

wonderwind271/gpt2-probe-finetune-UD-L4

Text Generation • 0.1B • Updated 1 day ago • 3

wonderwind271/childes-checkpoints

wonderwind271/childes-probing-tunedlens

wonderwind271/vsdiag-checkpoints

wonderwind271/gpt2-vsdiag-1

Text Generation • 0.1B • Updated Mar 29 • 8

wonderwind271/gpt2-childes-v4

Text Generation • 0.2B • Updated Mar 28 • 9

wonderwind271/gpt2-childes-v2

Text Generation • 0.2B • Updated Feb 10 • 9

wonderwind271/gpt2-childes-v1

Text Generation • 0.1B • Updated Feb 7 • 8

wonderwind271/gpt2-ACL-series

Text Generation • 0.1B • Updated Feb 4 • 7

wonderwind271/wordlevel-tokenizer

wonderwind271/babylm-raw-tokenizer

wonderwind271/glm-4-sft-v2

Feature Extraction • 9B • Updated Jul 31, 2024 • 5

wonderwind271/glm-4-sft-lora

Updated Jul 25, 2024

wonderwind271/glm-4-sft

Feature Extraction • 9B • Updated Jul 25, 2024 • 6

wonderwind271/glm4-sft

Updated Jul 25, 2024