Views
No views yet
0: O
1: B-DebtInstrumentBasisSpreadOnVariableRate1
2: B-DebtInstrumentFaceAmount
3: I-DebtInstrumentFaceAmount
4: I-LineOfCreditFacilityMaximumBorrowingCapacity
5: B-DebtInstrumentInterestRateStatedPercentage
6: I-DebtInstrumentBasisSpreadOnVariableRate1
7: I-DebtInstrumentInterestRateStatedPercentage
8: B-LineOfCreditFacilityMaximumBorrowingCapacity1from transformers import AutoTokenizer, AutoModelForTokenClassification
2
3# Preparing labels for reference
4int2str = {
5 0: 'O',
6 1: 'B-DebtInstrumentBasisSpreadOnVariableRate1',
7 2: 'B-DebtInstrumentFaceAmount',
8 3: 'I-DebtInstrumentFaceAmount',
9 4: 'I-LineOfCreditFacilityMaximumBorrowingCapacity',
10 5: 'B-DebtInstrumentInterestRateStatedPercentage',
11 6: 'I-DebtInstrumentBasisSpreadOnVariableRate1',
12 7: 'I-DebtInstrumentInterestRateStatedPercentage',
13 8: 'B-LineOfCreditFacilityMaximumBorrowingCapacity',
14}
15
16str2int = {v:k for k,v in int2str.items()}
17
18# Load model dependencies
19model = AutoModelForTokenClassification.from_pretrained(
20 "brolaurens/finer-distilbert", num_labels=len(int2str), id2label=int2str, label2id=str2int
21)
22
23tokenizer = AutoTokenizer.from_pretrained("distilbert/distilbert-base-uncased", model_max_length=512)
24
25# Text
26texts = [
27 "Of the amount drawn, $ 3,721,583 was used to pay the principal amount of $ 3,700,000 and accrued interest of $ 21,583 due under the Company 's Loan Agreement with Capital Preservation Solutions, LLC entered into on September 4, 2015."
28]
29
30# Tokenize input
31model_input = tokenizer(texts, return_tensors='pt')
32
33# Obtain model output
34predictions = model(**model_input).logits
35predictions = predictions.argmax(axis=2)
36predicted_labels = [[int2str[x] for x in t] for t in predictions.tolist()]base_model: distilbert/distilbert-base-uncased
learning_rate: 2e-5
batch_size: 32
epochs: 3
optimizer: adamw
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
loss_function: cross entropy loss