| # 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: gpt_dialogue | |
| # pretrained: "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_caption_capfilt_large.pth" | |
| # pretrained: "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_capfilt_large.pth" | |
| len_tokenizer: 50264 # 50257 tokens from gpt2 default tokenizer + additional special tokens | |
| len_video_ft: 4224 # i3d_rgb: 2048 i3d_flow: 2048 vggish: 128 | |
| preprocess: | |
| vis_processor: | |
| train: | |
| name: "gpt_video_ft" | |
| eval: | |
| name: "gpt_video_ft" | |
| text_processor: | |
| train: | |
| name: "gpt_dialogue" | |
| eval: | |
| name: "gpt_dialogue" |