Upload 3 files

Dockerfile

@@ -0,0 +1,10 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 🔥 Expose port (Spaces uses 7860)
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,64 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+app = FastAPI(
+    title="Check-in Detail Classifier API",
+    description="Classifies check-ins as DETAILED or NOT_DETAILED",
+    version="1.0"
+)
+
+# Load model once (efficient)
+MODEL_NAME = "mjpsm/checkin-detail-classifier"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
+
+model.eval()
+
+# Request schema
+class Request(BaseModel):
+    text: str
+
+# Root route
+@app.get("/")
+def root():
+    return {
+        "message": "Welcome to the Check-in Detail Classifier API"
+    }
+
+# Classification logic
+def classify(text: str):
+    inputs = tokenizer(
+        text,
+        return_tensors="pt",
+        truncation=True,
+        padding=True
+    )
+
+    # Remove token_type_ids (DistilBERT fix)
+    inputs.pop("token_type_ids", None)
+
+    with torch.no_grad():
+        outputs = model(**inputs)
+
+    probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+
+    pred = torch.argmax(probs).item()
+    confidence = probs[0][pred].item()
+
+    label = model.config.id2label[pred]
+
+    return label, confidence
+
+# Predict endpoint
+@app.post("/predict")
+def predict(req: Request):
+    label, confidence = classify(req.text)
+
+    return {
+        "input": req.text,
+        "prediction": label,
+        "confidence": round(confidence, 4)
+    }

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+transformers
+torch