Upload 2 files

app.py

@@ -0,0 +1,54 @@
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+
+roberta_model = AutoModelForSequenceClassification.from_pretrained("roberta-base")
+roberta_tokenizer = AutoTokenizer.from_pretrained("roberta-base")
+
+# Load BERT model and tokenizer
+bert_model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased")
+bert_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
+
+app = FastAPI()
+
+class TextData(BaseModel):
+    text: str
+
+# Helper function to make predictions and convert to 0 (human) or 100 (AI)
+def predict_text(model, tokenizer, text):
+    # Preprocess the text
+    inputs = tokenizer(text, truncation=True, padding='max_length', max_length=128, return_tensors='pt')
+
+    # Move to the correct device (GPU/CPU)
+    device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+    model.to(device)
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+
+    # Get model predictions
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Convert logits to probabilities
+    logits = outputs.logits
+    probabilities = torch.softmax(logits, dim=-1)
+    predicted_class = torch.argmax(probabilities, dim=-1).item()
+    #ai_prob = probabilities[0][1].item() * 100
+    #print(ai_prob)
+    # Return 0 for human, 100 for AI
+    return 100 if predicted_class == 1 else 0
+
+# Endpoint to predict with RoBERTa
+@app.post("/predict_copyleaks_V1")
+def predict_roberta(data: TextData):
+    predicted_value = predict_text(roberta_model, roberta_tokenizer, data.text)
+    return {"text": data.text, "Score": predicted_value}
+
+# Endpoint to predict with BERT
+@app.post("/predict_copyleaks_V2")
+def predict_bert(data: TextData):
+    predicted_value = predict_text(bert_model, bert_tokenizer, data.text)
+    return {"text": data.text, "Score": predicted_value}
+

requirements.txt

@@ -0,0 +1,38 @@
+annotated-types==0.7.0
+anyio==4.6.0
+certifi==2024.8.30
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+fastapi==0.115.0
+filelock==3.16.1
+fsspec==2024.9.0
+h11==0.14.0
+httptools==0.6.1
+huggingface-hub==0.25.1
+idna==3.10
+Jinja2==3.1.4
+MarkupSafe==2.1.5
+mpmath==1.3.0
+networkx==3.3
+numpy==2.1.1
+packaging==24.1
+pydantic==2.9.2
+pydantic_core==2.23.4
+python-dotenv==1.0.1
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+safetensors==0.4.5
+sniffio==1.3.1
+starlette==0.38.6
+sympy==1.13.3
+tokenizers==0.20.0
+torch==2.4.1
+tqdm==4.66.5
+transformers==4.45.1
+typing_extensions==4.12.2
+urllib3==2.2.3
+uvicorn==0.31.0
+watchfiles==0.24.0
+websockets==13.1