Open JiahuiKChen opened 3 months ago
When using the given model initialization 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 )
the model should be initialized
Failure with 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
ValueError: We require the attribute name for the nn.ModuleList in the decoder storing the transformer block layers. Please supply this string manually.
Run any of the create_model_and_transforms code snippets.
create_model_and_transforms
I'm getting errors for all the models. Different error for 4B models, see report here.
Python 3.12.3 transformers 4.41.2 torch 2.3.1
No changes made, no code other than the import and initialization method
I use pip install transformers==4.30.2 and then it worked.
pip install transformers==4.30.2
Expected Behavior
When using the given model initialization code:
the model should be initialized
Current Behavior
Failure with 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/d3695f31bcf7702bdf0c4ea86a57a77bSteps to Reproduce
Run any of the
create_model_and_transforms
code snippets.I'm getting errors for all the models. Different error for 4B models, see report here.
Environment
Detailed Description
No changes made, no code other than the import and initialization method