Upload README.md

README.md

@@ -11,8 +11,6 @@ language:
 
 This model is fine-tuned for binary text classification of Supportive Interactions in Instant Messenger dialogs of Adolescents in Czech. 
 
-## Model Details
-
 ### Model Description
 
 The model was fine-tuned on a Czech dataset of Instant Messenger dialogs of Adolescents. The classification is binary and the model outputs probablities for labels {0,1}: Supportive Interactions present or not.
@@ -33,21 +31,24 @@ Here is how to use this model to classify a context-window of a dialogue:
 
 ```python
 import numpy as np
-from transformers import AutoTokenizer, RobertaForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
 
 # Prepare input texts. This model is pretrained and fine-tuned for Czech
 test_texts = ['Utterance1;Utterance2;Utterance3']
 
-
 # Load the model and tokenizer
-model = RobertaForSequenceClassification.from_pretrained('chi2024/robeczech-base-binary-cs-iib',
-                                                           num_labels=2).to("cuda")
-tokenizer = AutoTokenizer.from_pretrained('chi2024/robeczech-base-binary-cs-iib', use_fast=False, truncation_side='left')
+model = AutoModelForSequenceClassification.from_pretrained(
+    'chi2024/robeczech-base-binary-cs-iib', num_labels=2).to("cuda")
+
+tokenizer = AutoTokenizer.from_pretrained(
+    'chi2024/robeczech-base-binary-cs-iib',
+    use_fast=False, truncation_side='left')
 assert tokenizer.truncation_side == 'left'
 
 # Define helper functions
 def get_probs(text, tokenizer, model):
-    inputs = tokenizer(text, padding=True, truncation=True, max_length=256, return_tensors="pt").to("cuda")
+    inputs = tokenizer(text, padding=True, truncation=True, max_length=256,
+                       return_tensors="pt").to("cuda")
     outputs = model(**inputs)
     return outputs[0].softmax(1)
 
@@ -57,8 +58,9 @@ def preds2class(probs, threshold=0.5):
     return pclasses.argmax(-1)
 
 def print_predictions(texts):
-    probabilities = [get_probs(texts[i], tokenizer, model).cpu().detach().numpy()[0] for i in
-                     range(len(texts))]
+    probabilities = [get_probs(
+        texts[i], tokenizer, model).cpu().detach().numpy()[0]
+                     for i in range(len(texts))]
     predicted_classes = preds2class(np.array(probabilities))
     for c, p in zip(predicted_classes, probabilities):
         print(f'{c}: {p}')