2 2

Ge Shi

geshijoker

https://geshijoker.github.io/

geshijoker

AI & ML interests

CV, NLP, LLM, XAI

Recent Activity

published a model 7 days ago

geshijoker/my_mnist_model

updated a model 7 days ago

geshijoker/MyRepo

published a model 7 days ago

geshijoker/MyRepo

View all activity

Organizations

None yet

geshijoker's activity

published a model 7 days ago

geshijoker/my_mnist_model

Updated 7 days ago

updated a model 7 days ago

geshijoker/MyRepo

Updated 7 days ago • 14

published a model 7 days ago

geshijoker/MyRepo

Updated 7 days ago • 14

updated a model 2 months ago

geshijoker/HealthCareMagic_sft_llama3_instruct_full

Text Generation • Updated Dec 31, 2024 • 36

updated 2 collections 2 months ago

ChatDoctor

Collection

A collection of finetuned LLM models on the ChatDoctor HealthCareMagic dataset • 5 items • Updated Dec 31, 2024

MiniLlava

Collection

A collection of small-size VLM finetuned from a vision tower model and a causal LM • 1 item • Updated Dec 30, 2024

updated 2 models 2 months ago

geshijoker/nanoLlava-dpo

Image-Text-to-Text • Updated Dec 30, 2024

geshijoker/HealthCareMagic_sft_llama3_qlora_all

Updated Dec 30, 2024 • 1

updated a collection 2 months ago

ChatDoctor

Collection

A collection of finetuned LLM models on the ChatDoctor HealthCareMagic dataset • 5 items • Updated Dec 31, 2024

updated a model 2 months ago

geshijoker/HealthCareMagic_sft_llama3_lora_all

Updated Dec 29, 2024 • 1

updated a collection 2 months ago

ChatDoctor

Collection

A collection of finetuned LLM models on the ChatDoctor HealthCareMagic dataset • 5 items • Updated Dec 31, 2024

updated 2 models 2 months ago

geshijoker/HealthCareMagic_sft_llama3_instruct_qlora_all

Updated Dec 29, 2024 • 10

geshijoker/HealthCareMagic_sft_llama3_instruct_lora_all

Updated Dec 29, 2024 • 2

upvoted an article 6 months ago

Article

From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate

Jun 13, 2024

• 47

updated a model 6 months ago

geshijoker/idefics2-8b-dpo-RLHF-V

Updated Sep 10, 2024

New activity in openbmb/RLAIF-V-Dataset 6 months ago

Error when generating the "train" split

#5 opened 6 months ago by

geshijoker

updated 2 models 6 months ago

geshijoker/blip2-opt-2.7b-MSCOCO-2017

Updated Sep 9, 2024

geshijoker/vit-base-patch16-224-in21k-AdaLora

Updated Sep 6, 2024 • 1