Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
alexshengzhili
/
llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-6-avg-False-epoch-3
like
0
PEFT
llava
Model card
Files
Files and versions
Community
1
Use this model
refs/pr/1
llava-lora-dpo-1227lrvtail2000_sft-self-sampled-beta-0.5-lr-5e-6-avg-False-epoch-3
/
README.md
osanseviero
Specify right model card metadata
9450189
verified
8 months ago
preview
code
|
raw
Copy download link
history
blame
Safe
135 Bytes
metadata
library_name:
peft
tags:
-
llava
pipeline_tag:
image-text-to-text
Training procedure
Framework versions
PEFT 0.4.0