Unable to download your finetuned Bert model about goemotions-pytorch HOT 5 CLOSED

https://huggingface.co/monologg/bert-base-cased-goemotions-ekman
https://huggingface.co/monologg/bert-base-cased-goemotions-group
https://huggingface.co/monologg/bert-base-cased-goemotions-original

Please see List all files in model in pages above.

from goemotions-pytorch.

I tried to download all the files and use it for prediction as shown in your github readme. It is showing me
UnicodeDecodeError : 'utf-8' codec can't decode byte : invalid continuation byte. Please let me know how to fix this.

from goemotions-pytorch.

I tried to download all the files and use it for prediction as shown in your github readme. It is showing me
UnicodeDecodeError : 'utf-8' codec can't decode byte : invalid continuation byte. Please let me know how to fix this.

First of all, you don't have to download the files manually. If you run the code below, all the files will be downloaded automatically from huggingface s3

from transformers import BertTokenizer
from model import BertForMultiLabelClassification
from multilabel_pipeline import MultiLabelPipeline
from pprint import pprint

tokenizer = BertTokenizer.from_pretrained("monologg/bert-base-cased-goemotions-original")
model = BertForMultiLabelClassification.from_pretrained("monologg/bert-base-cased-goemotions-original")

goemotions = MultiLabelPipeline(
    model=model,
    tokenizer=tokenizer,
    threshold=0.3
)

texts = [
    "Hey that's a thought! Maybe we need [NAME] to be the celebrity vaccine endorsement!",
    "it’s happened before?! love my hometown of beautiful new ken 😂😂",
    "I love you, brother.",
    "Troll, bro. They know they're saying stupid shit. The motherfucker does nothing but stink up libertarian subs talking shit",
]

pprint(goemotions(texts))

Plz run this code and write all the logs you got:)

from goemotions-pytorch.

from goemotions-pytorch.

I can't infer the reason only based on the one line of the log that you gave. (UnicodeDecodeError : 'utf-8' codec can't decode byte : invalid continuation byte)

You should give all the log from console.

What I can only guess is that you might not save the file (vocab.txt etc) in utf-8 format.

Can you check the encoding of the files?

from goemotions-pytorch.