f

app.py

@@ -1,46 +1,32 @@
 import gradio as gr
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
+from transformers import AutoTokenizer, AutoConfig, AutoModelForSequenceClassification
 
-# Model and tokenizer loading
-model_id = "cheberle/autotrain-35swc-b4r9z"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForSequenceClassification.from_pretrained(model_id)
+# Load model and tokenizer
+model_name = "cheberle/autotrain-35swc-b4r9z"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-# Move model to GPU if available
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model = model.to(device)
+# Explicitly define the model configuration if needed
+config = AutoConfig.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name, config=config)
 
-def predict(text):
-    # Tokenize input
-    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
-    
-    # Move inputs to same device as model
-    inputs = {k: v.to(device) for k, v in inputs.items()}
-    
-    # Get prediction
-    with torch.no_grad():
-        outputs = model(**inputs)
-        predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
-    
-    # Get prediction probabilities and labels
-    probs = predictions[0].tolist()
-    labels = model.config.id2label
-    
-    # Create formatted output
-    results = {labels[i]: float(probs[i]) for i in range(len(probs))}
-    
-    return results
+# Inference function
+def classify_text(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt", padding=True, truncation=True)
+    outputs = model(**inputs)
+    probabilities = outputs.logits.softmax(dim=-1).tolist()[0]
+    labels = {i: f"Label {i}" for i in range(len(probabilities))}  # Define label mapping if needed
+    result = {labels[i]: prob for i, prob in enumerate(probabilities)}
+    return result
 
-# Create Gradio interface
-iface = gr.Interface(
-    fn=predict,
-    inputs=gr.Textbox(label="Input Text"),
-    outputs=gr.Label(label="Prediction"),
-    title="Model Prediction Interface",
-    description=f"Enter text to get predictions from {model_id}",
-    examples=["Example text to try"]
+# Gradio interface
+interface = gr.Interface(
+    fn=classify_text,
+    inputs="text",
+    outputs="label",
+    title="DeepSeek-R1 Text Classification",
+    description="Classify text inputs using the DeepSeek-R1 model."
 )
 
-# Launch the interface
-iface.launch()
+# Launch the app
+if __name__ == "__main__":
+    interface.launch()