Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt .
+
+# Install CPU-only PyTorch (much smaller than GPU build), then the rest
+RUN pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu && \
+    pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README.md

@@ -3,9 +3,7 @@ title: CodeSheriff Inference
 emoji: 🔍
 colorFrom: blue
 colorTo: red
-sdk: gradio
-sdk_version: "4.44.0"
-python_version: "3.11"
-app_file: app.py
+sdk: docker
+app_port: 7860
 pinned: false
 ---

app.py

@@ -1,13 +1,14 @@
 """
 CodeSheriff Inference Space
 
-A lightweight Gradio app that loads the fine-tuned CodeBERT classifier
-and exposes a /predict API endpoint.  Called remotely by the Render backend.
+Minimal FastAPI server that loads the fine-tuned CodeBERT classifier
+and exposes a POST /predict endpoint.  Called remotely by the Render backend.
 """
 
-import gradio as gr
 import torch
+from fastapi import FastAPI
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import uvicorn
 
 MODEL_ID = "jayansh21/codesheriff-bug-classifier"
 NUM_LABELS = 5
@@ -20,6 +21,8 @@ LABEL_NAMES = {
     4: "Logic Flaw",
 }
 
+app = FastAPI(title="CodeSheriff Inference")
+
 print("Loading CodeSheriff classifier …")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForSequenceClassification.from_pretrained(
@@ -29,13 +32,15 @@ model.eval()
 print("Model loaded ✅")
 
 
-def predict(code_snippet: str) -> dict:
+@app.post("/predict")
+def predict(data: dict):
     """Classify a code snippet and return label, confidence, label_id."""
-    if not code_snippet or not code_snippet.strip():
+    code = data.get("code", "")
+    if not code or not code.strip():
         return {"label": "Clean", "confidence": 0.0, "label_id": 0}
 
     encoding = tokenizer(
-        code_snippet,
+        code,
         truncation=True,
         padding="max_length",
         max_length=MAX_LENGTH,
@@ -55,13 +60,10 @@ def predict(code_snippet: str) -> dict:
     }
 
 
-demo = gr.Interface(
-    fn=predict,
-    inputs=gr.Textbox(label="Code Snippet", lines=5, placeholder="Paste code here …"),
-    outputs=gr.JSON(label="Classification"),
-    title="🔍 CodeSheriff Bug Classifier",
-    description="Fine-tuned CodeBERT model for detecting common bug patterns.",
-    api_name="predict",
-)
+@app.get("/health")
+def health():
+    return {"status": "ok"}
+
 
-demo.launch()
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)

requirements.txt

@@ -1,3 +1,3 @@
---extra-index-url https://download.pytorch.org/whl/cpu
-torch
 transformers
+fastapi
+uvicorn