---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/model-cards
license: mit
language:
- cs
---
# Model Card for small-e-czech-2stage-supportive-interactions-cs

<!-- Provide a quick summary of what the model is/does. -->

This model is fine-tuned for 2nd stage multi-label text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents - it expects inputs where at least one of the classes appears. 

## Model Description

The model was fine-tuned on a dataset of Instant Messenger dialogs of Adolescents. The classification is 2stage and the model outputs probablities for labels {0,1,2,3,4}: 

0. Informational Support
1. Emotional Support
2. Social Companionship
3. Appraisal
4. Instrumental Support

- **Developed by:** Anonymous
- **Language(s):** cs
- **Finetuned from:** small-e-czech

## Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/justtherightsize/supportive-interactions-and-risks
- **Paper:** Stay tuned!

## Usage
Here is how to use this model to classify a context-window of a dialogue:

```python
import numpy as np
import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# Prepare input texts. This model is pretrained on multi-lingual data 
# and fine-tuned on English
test_texts = ['Utterance1;Utterance2;Utterance3']

# Load the model and tokenizer
model = AutoModelForSequenceClassification.from_pretrained(
    'justtherightsize/small-e-czech-2stage-supportive-interactions-cs', num_labels=5).to("cuda")

tokenizer = AutoTokenizer.from_pretrained(
    'justtherightsize/small-e-czech-2stage-supportive-interactions-cs',
    use_fast=False, truncation_side='left')
assert tokenizer.truncation_side == 'left'

# Define helper functions
def predict_one(text: str, tok, mod, threshold=0.5):
    encoding = tok(text, return_tensors="pt", truncation=True, padding=True,
                   max_length=256)
    encoding = {k: v.to(mod.device) for k, v in encoding.items()}
    outputs = mod(**encoding)
    logits = outputs.logits
    sigmoid = torch.nn.Sigmoid()
    probs = sigmoid(logits.squeeze().cpu())
    predictions = np.zeros(probs.shape)
    predictions[np.where(probs >= threshold)] = 1
    return predictions, probs

def print_predictions(texts):
    preds = [predict_one(tt, tokenizer, model) for tt in texts]
    for c, p in preds:
        print(f'{c}: {p.tolist():.4f}')

# Run the prediction
print_predictions(test_texts)
```