Created
June 25, 2023 22:38
-
-
Save smellslikeml/435c0398bab82bb59f12c74c0a07b507 to your computer and use it in GitHub Desktop.
Video-LLaMA eval config for Colab
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
model: | |
arch: video_llama | |
model_type: pretrain_vicuna | |
freeze_vit: True | |
freeze_qformer: True | |
max_txt_len: 160 | |
end_sym: "###" | |
low_resource: True | |
frozen_llama_proj: False | |
llama_model: "/content/vicuna-13b/" | |
llama_proj_model: '/content/pretrained_minigpt4.pth' | |
fusion_head_layers: 2 | |
max_frame_pos: 32 | |
fusion_header_type: "seqTransf" | |
ckpt: '/content/pretrain-vicuna13b.pth' | |
datasets: | |
webvid: | |
vis_processor: | |
train: | |
name: "alpro_video_eval" | |
n_frms: 8 | |
image_size: 224 | |
text_processor: | |
train: | |
name: "blip_caption" | |
run: | |
task: video_text_pretrain |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment