f

app.py

@@ -1,64 +1,46 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Model and tokenizer loading
+model_id = "cheberle/autotrain-35swc-b4r9z"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
+
+# Move model to GPU if available
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = model.to(device)
+
+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
+
+# 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"]
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the interface
+iface.launch()

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+gradio
+torch
+transformers