openflamingo

/

OpenFlamingo-9B-vitl-mpt7b

like 42

Follow

openflamingo 33

When using the given model init code:

from open_flamingo import create_model_and_transforms

model, image_processor, tokenizer = create_model_and_transforms(
clip_vision_encoder_path="ViT-L-14",
clip_vision_encoder_pretrained="openai",
lang_encoder_path="anas-awadalla/mpt-7b",
tokenizer_path="anas-awadalla/mpt-7b",
cross_attn_every_n_layers=4
)

I get an error:
ValueError: We require the attribute name for the nn.ModuleList in the decoder storing the transformer block layers. Please supply this string manually.
Full error output here: https://gist.github.com/JiahuiKChen/d3695f31bcf7702bdf0c4ea86a57a77b

I'm unable to use the model, or figure out how to provide an attribute name to the model.
I get the same error when trying to initialize openflamingo/OpenFlamingo-3B-vitl-mpt1b