arxiv:2503.12440
Jed Cheng PRO
jed351
AI & ML interests
Cantonese used in Hong Kong
Organizations
models 17
jed351/Gemma3-4B-ChatVector_SFT-from-IT_and_IT
4B • Updated • 5
jed351/gemma3-maxtext-conversion-test
4B • Updated • 4
jed351/Gemma3-4B-SFT-from-IT
Image-Text-to-Text • 4B • Updated
jed351/Gemma3-4B-cpt-v2
4B • Updated • 2
jed351/cc_llama4
Updated
jed351/deberta-v3-large
Updated
jed351/gpt2-rthk
Text Generation • 0.1B • Updated • 7
jed351/whisper-large-v2-LORA-zh-HK
Updated
jed351/gpt2_base_zh-hk-shikoto
Text Generation • Updated • 8 • 2
jed351/gpt2_base_zh-hk-lihkg
Text Generation • Updated • 33 • 3
datasets 11
jed351/Traditional-Chinese-Common-Crawl-by-year
Viewer • Updated • 15.5M • 7
jed351/Cantonese_Common_Crawl_Filtered
Viewer • Updated • 5.65M • 203 • 4
jed351/Traditional-Chinese-Common-Crawl-Filtered
Viewer • Updated • 278M • 5.31k • 24
jed351/Traditional-Chinese-Common-Crawl-NOT-Cleaned
Viewer • Updated • 547M • 1.11k
jed351/Cantonese-Web-Data
Viewer • Updated • 732k • 18 • 4
jed351/fineweb-ja-keyword-hk
Viewer • Updated • 2.08M • 462
jed351/finepdfs-traditional-chinese
Viewer • Updated • 1.31M • 136
jed351/Chinese-Common-Crawl-Filtered
Viewer • Updated • 21.3M • 258 • 18
jed351/rthk_news
Viewer • Updated • 332k • 31 • 6
jed351/shikoto_zh_hk
Viewer • Updated • 144k • 6 • 2