MiniGPT-4/minigpt4/configs/models/blip2/blip2_pretrain.yaml
2023-12-01 23:17:44 +08:00

43 lines
1.1 KiB
YAML

# 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
image_size: 336
drop_path_rate: 0
use_grad_checkpoint: False
vit_precision: "fp16"
freeze_vit: True
# Q-Former
num_query_token: 32
# moe
# moebert_expert_num: 20
# moebert_route_method: "gate-sentence"
# moebert_load_balance: 0.05
# moe_topk: 2
preprocess:
vis_processor:
train:
name: "blip_image_train"
image_size: 336
eval:
name: "blip_image_eval"
image_size: 336
text_processor:
train:
name: "blip_caption"
eval:
name: "blip_caption"