Update app.py

app.py

@@ -2,35 +2,42 @@ from transformers import TextClassificationPipeline, AutoTokenizer, AutoModelFor
 import gradio as gr
 import os
 
-# def get_model(model_name='Overfit-GM/temp_dist'):
-#     id2label = {0: 'INSULT', 1: 'OTHER',
-#                 2: 'PROFANITY', 3: 'RACIST', 4: 'SEXIST'}
-#     label2id = {v: k for k, v in id2label.items()}
-#     tokenizer = AutoTokenizer.from_pretrained(model_name)
-#     model = AutoModelForSequenceClassification.from_pretrained(model_name,
-#                                                                problem_type="single_label_classification",
-#                                                                id2label=id2label,
-#                                                                label2id=label2id,
-#                                                                num_labels=5,
-#                                                                output_hidden_states=False,
-#                                                                )
-#     return model, tokenizer
-
-
 models = [
-    "Overfit-GM/temp_dist",
-    "Overfit-GM/bert-base-turkish-cased-offensive"
+    "Overfit-GM/bert-base-turkish-cased-offensive",
+    "Overfit-GM/bert-base-turkish-uncased-offensive",
+    "Overfit-GM/bert-base-turkish-128k-cased-offensive",
+    "Overfit-GM/bert-base-turkish-128k-uncased-offensive",
+    "Overfit-GM/convbert-base-turkish-mc4-cased-offensive",
+    "Overfit-GM/convbert-base-turkish-mc4-uncased-offensive",
+    "Overfit-GM/convbert-base-turkish-cased-offensive",
+    "Overfit-GM/distilbert-base-turkish-cased-offensive",
+    "Overfit-GM/electra-base-turkish-cased-discriminator-offensive",
+    "Overfit-GM/electra-base-turkish-mc4-cased-discriminator-offensive",
+    "Overfit-GM/electra-base-turkish-mc4-uncased-discriminator-offensive",
+    "Overfit-GM/xlm-roberta-large-turkish-offensive",
+    "Overfit-GM/mdeberta-v3-base-offensive"
 ]
 
 model_box=[
     gr.load(models[0], src='models', hf_token=os.environ['API_KEY']),
     gr.load(models[1], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[2], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[3], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[4], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[5], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[6], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[7], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[8], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[9], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[10], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[11], src='models', hf_token=os.environ['API_KEY']),
+    gr.load(models[12], src='models', hf_token=os.environ['API_KEY'])
 ]
 
 def sentiment_analysis(text, model_choice):
     
-    a_variable = model_box[model_choice]
-    output = a_variable(text)
+    model = model_box[model_choice]
+    output = model(text)
     return output
 
 with gr.Blocks() as demo: