metadata
base_model: qresearch/doubutsu-2b-pt-756
library_name: peft
license: apache-2.0
datasets:
- google/docci
language:
- en
pipeline_tag: image-text-to-text
doubutsu-2b-lora-756-docci
An adapter for qresearch/doubutsu-2b-pt-756 on DOCCI for 3 epochs.
Usage
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
model_id = "qresearch/doubutsu-2b-pt-756"
model = AutoModelForCausalLM.from_pretrained(
model_id,
trust_remote_code=True,
torch_dtype=torch.float16,
).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(
model_id,
use_fast=True,
)
model.load_adapter("qresearch/doubutsu-2b-lora-756-docci")
image = Image.open("IMAGE")
print(
model.answer_question(
image, "Describe the image", tokenizer, max_new_tokens=128, temperature=0.1
),
)
Examples
| Image | Examples |
|---|---|
 |
Describe the image. A top-down view of a sidewalk with the word "ROW" in orange spray paint on the left side. A red fire lane symbol is below the word in the middle. A line is on the right side of the sidewalk, going up vertically. A metal strip is on the left side of the sidewalk, going horizontally. Dirt is on the ground in front of the sidewalk. |
 |
Describe the image. A low-angle view of a golden statue of a woman on top of a golden horse and a golden chariot. The woman is facing the right side of the image. She is holding a golden bird in her right hand and a golden shield in her left hand. She is wearing a golden robe with a golden belt around her waist. She is wearing a golden helmet on her head. She is holding a golden staff in her right hand and her left hand is raised up above her head, palm facing forward. The woman is wearing a golden crown on her head. The horse is facing the left side of the image. |
.x+=:.
z` ^% .uef^"
.u . . <k .u . :d88E
.u@u .d88B :@8c .u .@8Ned8" .u u .d88B :@8c . `888E
.zWF8888bx ="8888f8888r ud8888. .@^%8888" ud8888. us888u. ="8888f8888r .udR88N 888E .z8k
.888 9888 4888>'88" :888'8888. x88: `)8b. :888'8888. .@88 "8888" 4888>'88" <888'888k 888E~?888L
I888 9888 4888> ' d888 '88%" 8888N=*8888 d888 '88%" 9888 9888 4888> ' 9888 'Y" 888E 888E
I888 9888 4888> 8888.+" %8" R88 8888.+" 9888 9888 4888> 9888 888E 888E
I888 9888 .d888L .+ 8888L @8Wou 9% 8888L 9888 9888 .d888L .+ 9888 888E 888E
`888Nx?888 ^"8888*" '8888c. .+ .888888P` '8888c. .+ 9888 9888 ^"8888*" ?8888u../ 888E 888E
"88" '888 "Y" "88888% ` ^"F "88888% "888*""888" "Y" "8888P' m888N= 888>
88E "YP' "YP' ^Y" ^Y' "P' `Y" 888
98> J88"
'8 @%
` :"