Ken Tsui's picture

Ken Tsui

kenhktsui

·

https://kenhktsui.github.io/

AI & ML interests

ML engineer, researcher VLM, LLM benchmark Opinions are my own

Recent Activity

upvoted a paper 11 days ago

Diffusion Transformers with Representation Autoencoders

upvoted a paper 17 days ago

Less is More: Recursive Reasoning with Tiny Networks

authored a paper 23 days ago

MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources

View all activity

Organizations

kenhktsui 's models 34

kenhktsui/math-fasttext-classifier

Text Classification • Updated Jul 3 • 46 • 2

kenhktsui/code-natural-language-fasttext-classifier

Text Classification • Updated Jul 3 • 282 • 2

kenhktsui/fineweb-edu-fasttext-classifier

Text Classification • Updated Jul 3 • 30 • 4

kenhktsui/llm-data-textbook-quality-fasttext-classifier-v2

Text Classification • Updated Jun 26 • 843 • 28

kenhktsui/finefineweb-domain-fasttext-classifier

Text Classification • Updated Mar 16 • 32 • 1

kenhktsui/Qwen2.5-3B-Instruct-GRPO-basic-sampling_temp_05

Text Generation • Updated Feb 14 • 3

kenhktsui/Qwen2.5-3B-Instruct-GRPO-minp-sampling_temp_05

Text Generation • Updated Feb 13

kenhktsui/Qwen-0.5B-GRPO

Text Generation • 0.5B • Updated Feb 12 • 1

kenhktsui/Qwen-0.5B-GRPO-gsm8k-count-wait-cap-cross-correct

Text Generation • 0.5B • Updated Feb 7 • 1

kenhktsui/llama3.1-8b-instruct-thinking-sft-merged-gguf

8B • Updated Dec 30, 2024 • 21 • 1

kenhktsui/llama3.1-8b-instruct-thinking-sft-merged

Text Generation • 8B • Updated Dec 30, 2024 • 1

kenhktsui/qwen2.5-7b-instruct-thinking-sft-merged

Text Generation • 8B • Updated Dec 30, 2024 • 1

kenhktsui/qwen2.5-7b-instruct-thinking-sft-merged-gguf

8B • Updated Dec 30, 2024 • 27 • 1

kenhktsui/qwen2.5-7b-instruct-thinking-sft

Updated Dec 30, 2024

kenhktsui/llama3.2-3b-instruct-thinking-sft-merged-gguf

3B • Updated Dec 24, 2024 • 15

kenhktsui/llama3.2-3b-instruct-thinking-sft-merged

Text Generation • 3B • Updated Dec 24, 2024 • 1

kenhktsui/llama3.2-3b-instruct-thinking-sft

Updated Dec 24, 2024

kenhktsui/setfit_test_toxic_chat

Text Classification • 0.1B • Updated Aug 18, 2024 • 1

kenhktsui/setfit_test_toxic_chat_syn

Text Classification • 0.1B • Updated Aug 18, 2024 • 1

kenhktsui/setfit_test_arxiv_classification

Text Classification • 0.1B • Updated Aug 18, 2024

kenhktsui/setfit_test_ag_news

Text Classification • 0.1B • Updated Aug 17, 2024

kenhktsui/setfit_test_ag_news_syn

Text Classification • 0.1B • Updated Aug 16, 2024 • 1

kenhktsui/setfit_test_arxiv_classification_syn

Text Classification • 0.1B • Updated Aug 16, 2024 • 1

kenhktsui/setfit_test_imdb

Text Classification • 0.1B • Updated Aug 15, 2024

kenhktsui/setfit_test_twitter_news_syn

Text Classification • 0.1B • Updated Aug 15, 2024

kenhktsui/setfit_test_twitter_news

Text Classification • 0.1B • Updated Aug 15, 2024

kenhktsui/fasttext_test

Updated Aug 4, 2024

kenhktsui/anyclassifier_setfit_demo

Text Classification • 0.1B • Updated Jul 30, 2024

kenhktsui/goformer-v0.1

Text Generation • 60.9M • Updated Jul 10, 2024 • 1 • 2

kenhktsui/llm-data-textbook-quality-fasttext-classifier-v1

Text Classification • Updated May 25, 2024 • 7 • 4