Could need some more documentation.

Issue still happens even with all those things.

Hey @PapayasTehSkeletor , as you may or may not have known, we've gotten access to the model. The torrent is available above this comment. I'm working on a way to use the model to inference and use CogView inside Colab.

Oh yeah. I think the problem is solved then. Will close this issue right now.

@PapayasTehSkeletor Colab with the direct download is here: https://colab.research.google.com/drive/1Bi2TnSUp2vNiSUhamsNuC4HqkZ2J4WwZ

Anyone could store the model in a mirror link like google drive?

Here you go @YukiSakuma , you can simply wget: https://the-eye.eu/public/AI/CogView/cogview-base.tar

My Colab featuring the link is here: https://colab.research.google.com/drive/1Bi2TnSUp2vNiSUhamsNuC4HqkZ2J4WwZ

/content/CogView Generate Samples WARNING: No training data specified using world size: 1 and model-parallel size: 1

using dynamic loss scaling initializing model parallel with size 1 initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 padded vocab (size: 58219) with 21 dummy tokens (new size: 58240) prepare tokenizer done building CogView2 model ... number of parameters on model parallel rank 0: 3928849920 current device: 0 tcmalloc: large alloc 7881007104 bytes == 0x5637e3fb2000 @ 0x7f61e428db6b 0x7f61e42ad379 0x7f6171f1e25e 0x7f6171f1f9d2 0x7f61aff48e7d 0x7f61c0b43120 0x7f61c0781bd9 0x5637152088a8 0x56371527bfd5 0x5637152767ad 0x5637152093ea 0x5637152773b5 0x5637152767ad 0x563715209003 0x563715208b09 0x56371535028d 0x5637152bf1db 0x563715207bb1 0x5637152f8fed 0x56371527b988 0x5637152767ad 0x563715148e2c 0x563715278bb5 0x5637152764ae 0x5637152093ea 0x56371527832a 0x56371520930a 0x5637152773b5 0x56371520930a 0x5637152773b5 0x5637152764ae Load model file pretrained/cogview/cogview-sr/20000/mp_rank_00_model_states.pt Working on No. 0 on 0... Traceback (most recent call last): File "generate_samples.py", line 326, in <module> main() File "generate_samples.py", line 323, in main generate_images_continually(model, args) File "generate_samples.py", line 215, in generate_images_continually for raw_text, seq, output_path in get_context(args, query_template): File "generate_samples.py", line 132, in get_context seq = _parse_and_to_tensor(raw_text, img_size=img_size, query_template=query_template) File "generate_samples.py", line 70, in _parse_and_to_tensor text = query_template.format(*text.split('\t')) IndexError: tuple index out of range /content

Ok ill close for now if something new happens ill reopen

From what I can understand, inside aze's colab, this is how it is done:

query_template = '[ROI1] {} [BASE] [BOI1] [Image]{}'
p = '一个漂亮的女人走在街上\t/content/CogView/samples/0.jpg'
text = query_template.format(*p.split('\t'))
text

Please follow the format in the readme.md, a.k.a. text\t{img_path}.

/content/CogView Generate Samples WARNING: No training data specified using world size: 1 and model-parallel size: 1

using dynamic loss scaling initializing model parallel with size 1 initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 3952 and data parallel seed: 1234 padded vocab (size: 58219) with 21 dummy tokens (new size: 58240) prepare tokenizer done building CogView2 model ... number of parameters on model parallel rank 0: 3928849920 current device: 0 tcmalloc: large alloc 7881007104 bytes == 0x5637e3fb2000 @ 0x7f61e428db6b 0x7f61e42ad379 0x7f6171f1e25e 0x7f6171f1f9d2 0x7f61aff48e7d 0x7f61c0b43120 0x7f61c0781bd9 0x5637152088a8 0x56371527bfd5 0x5637152767ad 0x5637152093ea 0x5637152773b5 0x5637152767ad 0x563715209003 0x563715208b09 0x56371535028d 0x5637152bf1db 0x563715207bb1 0x5637152f8fed 0x56371527b988 0x5637152767ad 0x563715148e2c 0x563715278bb5 0x5637152764ae 0x5637152093ea 0x56371527832a 0x56371520930a 0x5637152773b5 0x56371520930a 0x5637152773b5 0x5637152764ae Load model file pretrained/cogview/cogview-sr/20000/mp_rank_00_model_states.pt Working on No. 0 on 0... Traceback (most recent call last): File "generate_samples.py", line 326, in <module> main() File "generate_samples.py", line 323, in main generate_images_continually(model, args) File "generate_samples.py", line 215, in generate_images_continually for raw_text, seq, output_path in get_context(args, query_template): File "generate_samples.py", line 132, in get_context seq = _parse_and_to_tensor(raw_text, img_size=img_size, query_template=query_template) File "generate_samples.py", line 70, in _parse_and_to_tensor text = query_template.format(*text.split('\t')) IndexError: tuple index out of range /content

https://github.com/THUDM/CogView/issues/10#issuecomment-863590452 Please add a torrent download method in colab or update links. Also this works https://github.com/nishan7/Google-Colab-Torrent-Downloader with some modifications and its a way faster than wget.

Anyone could store the model in a mirror link like google drive?