|
|
--- |
|
|
library_name: transformers |
|
|
tags: [] |
|
|
--- |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
<!-- Provide a quick summary of what the model is/does. --> |
|
|
|
|
|
|
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
### How to use the model |
|
|
|
|
|
```python |
|
|
import pandas as pd |
|
|
import numpy as np |
|
|
from transformers import AutoModelForSequenceClassification, AutoTokenizer |
|
|
|
|
|
# Load model |
|
|
model = AutoModelForSequenceClassification.from_pretrained("lkonle/EMO_Anger_gbert") |
|
|
|
|
|
# Load tokenizer |
|
|
tokenizer = AutoTokenizer.from_pretrained("lkonle/EMO_Anger_gbert") |
|
|
tokenizer.pad_token = "[PAD]" |
|
|
tokenizer.add_special_tokens({'pad_token': '[PAD]'}) |
|
|
|
|
|
# define input text |
|
|
myinput = ["Paul war sehr sehr glücklich über seinen Welpen.", |
|
|
"Paul war sehr traurig über sein Frühstück.", |
|
|
"Paul hatte große Langeweile."] |
|
|
|
|
|
# tokenize, encode, format as batch and return pytorch tensors |
|
|
input_ids = tokenizer.batch_encode_plus(myinput, truncation=True, padding="max_length", padding_side="right", return_tensors="pt") |
|
|
|
|
|
# predict |
|
|
logits = model(**input_ids)["logits"] |
|
|
|
|
|
# get the predicted label |
|
|
result = logits.detach().numpy() |
|
|
prediction = np.argmax(result, axis=1) |
|
|
|
|
|
# store result in pandas |
|
|
output = pd.DataFrame() |
|
|
output["inputs"] = myinput |
|
|
output["prediction"] = prediction |
|
|
print(output) |
|
|
``` |
