Vision-CAIR's picture
Upload 48 files
b98ba2b
raw
history blame
597 Bytes
model:
arch: mini_gpt4
# vit encoder
image_size: 224
drop_path_rate: 0
use_grad_checkpoint: False
vit_precision: "fp16"
freeze_vit: True
freeze_qformer: True
# Q-Former
num_query_token: 32
# Vicuna
llama_model: "/path/to/vicuna/weights/"
# generation configs
prompt: ""
preprocess:
vis_processor:
train:
name: "blip2_image_train"
image_size: 224
eval:
name: "blip2_image_eval"
image_size: 224
text_processor:
train:
name: "blip_caption"
eval:
name: "blip_caption"