2023-10-30 08:13:28 +00:00
|
|
|
# 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: pretrain
|
|
|
|
|
load_finetuned: False
|
|
|
|
|
|
|
|
|
|
# pretrained: "https://storage.googleapis.com/sfr-vision-language-research/LAVIS/models/BLIP2/blip2_pretrained.pth"
|
|
|
|
|
pretrained: "/mnt/pfs-guan-ssai/nlu/wanghanzi/models/blip2/blip2_pretrained/blip2_pretrained.pth"
|
|
|
|
|
finetuned: ""
|
|
|
|
|
|
|
|
|
|
# vit encoder
|
2023-12-19 03:24:51 +00:00
|
|
|
image_size: 224
|
2023-10-30 08:13:28 +00:00
|
|
|
drop_path_rate: 0
|
|
|
|
|
use_grad_checkpoint: False
|
|
|
|
|
vit_precision: "fp16"
|
|
|
|
|
freeze_vit: True
|
|
|
|
|
|
|
|
|
|
# Q-Former
|
|
|
|
|
num_query_token: 32
|
|
|
|
|
|
2023-11-23 05:39:24 +00:00
|
|
|
# moe
|
2023-12-19 03:24:51 +00:00
|
|
|
use_moeqformer: True
|
|
|
|
|
use_route_moe: True
|
|
|
|
|
moebert_expert_num: 5
|
|
|
|
|
moebert_num_beams: 2
|
2023-10-30 08:13:28 +00:00
|
|
|
|
|
|
|
|
preprocess:
|
|
|
|
|
vis_processor:
|
|
|
|
|
train:
|
|
|
|
|
name: "blip_image_train"
|
2023-12-19 03:24:51 +00:00
|
|
|
image_size: 224
|
2023-10-30 08:13:28 +00:00
|
|
|
eval:
|
|
|
|
|
name: "blip_image_eval"
|
2023-12-19 03:24:51 +00:00
|
|
|
image_size: 224
|
2023-10-30 08:13:28 +00:00
|
|
|
text_processor:
|
|
|
|
|
train:
|
|
|
|
|
name: "blip_caption"
|
|
|
|
|
eval:
|
|
|
|
|
name: "blip_caption"
|
