Skip to content
/ multimodal_LLMs Public

Finetuning BLIP-2/ Flan-T5-xl for caption generation PEFT-LoRA

7 stars 0 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

AviSoori1x/multimodal_LLMs

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
README.md
README.md
 
 
Step 0: Pre-trained model BLIP2-flant5-xl.py
Step 0: Pre-trained model BLIP2-flant5-xl.py
 
 
Step 1: Generating descriptions.py
Step 1: Generating descriptions.py
 
 
Step 2: Generating images from descriptions.py
Step 2: Generating images from descriptions.py
 
 
Step 3: Finetuning image description generation model.py
Step 3: Finetuning image description generation model.py
 
 

Repository files navigation

multimodal_LLMs

Finetuning BLIP-2/ Flan-T5-xl for caption generation PEFT-LoRA. Used synthetic images generated using a diffusion model and a heuristic based prompting strategy

About

Finetuning BLIP-2/ Flan-T5-xl for caption generation PEFT-LoRA

Resources

Readme
Activity

Stars

7 stars

Watchers

3 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages