aisuko/sft-microsoft-phi2-on-dialogsum
Updated • 3
Bowen Li
aisuko
AI & ML interests
Developing theoretical foundations and practical algorithms for fair, interpretable, and causally-grounded machine learning systems.
Recent Activity
upvoted an article about 1 month ago
KV Caching Explained: Optimizing Transformer Inference Efficiency authored a paper about 2 months ago
The Missing Adapter Layer for Research Computing authored a paper about 2 months ago
Causal Prompting for Implicit Sentiment Analysis with Large Language ModelsOrganizations
aisuko/ft-distilGPT2-with-ELI5
Text Generation • 81.9M • Updated • 4
aisuko/ft-mistral-with-customize-ds-with-QLoRA
Updated • 4
aisuko/quantized-opt-125m-with-GPTQ
Text Generation • 0.1B • Updated • 5
aisuko/ft-bloomz-7b1-with-twitter-complaints-lora
Updated • 2 • 1
aisuko/int8-whisper-large-v2-common-voice-11
Updated • 2
aisuko/prefix-tuning-t5-large-with-sentences-allagree
Updated • 1
aisuko/prompt-tuning-bloomz-560m-twitter-complaints-raft-lora
Updated • 5
aisuko/p-tuning-roberta-large-with-mrpc
Updated • 3
aisuko/prompt-tuning-bloomz-560m-twitter-complaints-raft
Updated • 1
aisuko/ft-ms-git-base-pokemon-blip-captions
Image-Text-to-Text • 0.2B • Updated • 5
aisuko/ft-vilt-b32-mlm
Visual Question Answering • 0.1B • Updated • 17
aisuko/ft_bert_base_cased
Text Classification • 0.1B • Updated • 8
aisuko/ft-distilbert-base-uncased
Text Classification • 67M • Updated • 6
aisuko/demo_eli5_clm_model
Text Generation • 81.9M • Updated • 4
aisuko/ddpm-butterflies-128
Updated