Vision-CAIR's picture
Update minigpt4/configs/models/minigpt4.yaml
c93be5d
# Copyright (c) 2022, salesforce.com, inc.
# All rights reserved.
# SPDX-License-Identifier: BSD-3-Clause
# For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
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: "vicuna"
# 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"