Upload 4 files

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.10-slim
+
+WORKDIR /code
+
+COPY ./app /code/app
+
+RUN pip install --upgrade pip
+RUN pip install -r app/requirements.txt
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]

deberta_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdafeca39a5bdbb2b3b1dd7d628de614be1ad34d1064a6dfdec8884e999414bc
+size 556709919

main.py

@@ -0,0 +1,63 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import torch
+import torch.nn as nn
+import pickle
+from transformers import DebertaModel, DebertaTokenizer
+import uvicorn
+
+LABEL_COLUMNS = ['Red_Flag_Reason', 'Maker_Action', 'Escalation_Level',
+                 'Risk_Category', 'Risk_Drivers', 'Investigation_Outcome']
+DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+class InputText(BaseModel):
+    text: str
+
+with open("app/deberta_model.pkl", "rb") as f:
+    checkpoint = pickle.load(f)
+
+tokenizer = checkpoint['tokenizer']
+label_encoders = checkpoint['label_encoders']
+
+class DebertaMultiOutput(nn.Module):
+    def __init__(self, num_labels_per_output):
+        super().__init__()
+        self.deberta = DebertaModel.from_pretrained("microsoft/deberta-base")
+        self.dropout = nn.Dropout(0.3)
+        self.classifiers = nn.ModuleList([
+            nn.Linear(self.deberta.config.hidden_size, n_labels) for n_labels in num_labels_per_output
+        ])
+
+    def forward(self, input_ids, attention_mask):
+        outputs = self.deberta(input_ids=input_ids, attention_mask=attention_mask)
+        pooled = self.dropout(outputs.last_hidden_state[:, 0])
+        return [classifier(pooled) for classifier in self.classifiers]
+
+num_labels = [len(le.classes_) for le in label_encoders.values()]
+model = DebertaMultiOutput(num_labels)
+model.load_state_dict(checkpoint['model_state_dict'])
+model.to(DEVICE)
+model.eval()
+
+app = FastAPI()
+
+@app.get("/")
+def root():
+    return {"message": "🟢 DeBERTa multi-output classifier ready."}
+
+@app.post("/predict")
+def predict(input: InputText):
+    inputs = tokenizer(input.text, return_tensors="pt", truncation=True, padding=True, max_length=128)
+    input_ids = inputs['input_ids'].to(DEVICE)
+    attention_mask = inputs['attention_mask'].to(DEVICE)
+
+    with torch.no_grad():
+        outputs = model(input_ids, attention_mask)
+
+    preds = {}
+    for output, col, le in zip(outputs, LABEL_COLUMNS, label_encoders.values()):
+        pred_idx = torch.argmax(output, dim=1).item()
+        pred_label = le.inverse_transform([pred_idx])[0]
+        preds[col] = pred_label
+
+    return preds

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+torch
+transformers
+scikit-learn