Получите предупреждение: вы, вероятно, должны обучить эту модель на нижестоящей задаче, чтобы иметь возможность использо ⇐ Python

[Anonymous]

Я получаю это сообщение при загрузке модели BERT Finetune с прямой нейронной сетью на последнем уровне из каталога контрольной точки. < /p>
This IS expected if you are initializing FlaubertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing FlaubertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
Some weights of FlaubertForSequenceClassification were not initialized from the model checkpoint at /gpfswork/rech/kpf/umg16uw/results_hf/sm/checkpoint-10 and are newly initialized: ['sequence_summary.summary.weight', 'sequence_summary.summary.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
< /code>
На самом деле модель, уже обученная огромному набору данных, и я загрузил ее для выполнения вывода в новом наборе данных. < /p>

model = XXXForSequenceClassification.from_pretrained(modelForClass, num_labels=3)

test_file = '/g/012.xml'
modelForClass = '/g/checkpoint-10'

test = preprare_data(PRE_TRAINED_MODEL_NAME, test_file)
pred = predict(test, test_model)

< /code>
***** Running Prediction *****
Num examples = 5
Batch size = 8
0%| | 0/1 [00:00

Подробнее здесь: https://stackoverflow.com/questions/703 ... k-to-be-ab