Upload 6 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,31 @@
+# Use an official Python runtime as a parent image
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the application code
+COPY . .
+
+# Create necessary directories
+RUN mkdir -p saved_models tokenizer predictions
+
+# Download the BERT tokenizer
+RUN python -c "from transformers import BertTokenizer; BertTokenizer.from_pretrained('bert-base-uncased', cache_dir='./tokenizer')"
+
+# Expose the port the app runs on
+EXPOSE 8000
+
+# Command to run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"] 

README.md

@@ -1,10 +1,10 @@
----
-title: Bert New
-emoji: 🏃
-colorFrom: red
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Bert New
+emoji: 🏃
+colorFrom: red
+colorTo: blue
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,66 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import torch
+from transformers import BertTokenizer
+from models.bert_model import BertMultiOutputModel
+from config import TEXT_COLUMN, LABEL_COLUMNS, MAX_LEN, DEVICE
+from dataset_utils import load_label_encoders
+import numpy as np
+
+app = FastAPI()
+
+# Load the model and tokenizer
+model_path = "BERT_model.pth"
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model = BertMultiOutputModel([len(load_label_encoders()[col].classes_) for col in LABEL_COLUMNS]).to(DEVICE)
+model.load_state_dict(torch.load(model_path, map_location=DEVICE))
+model.eval()
+
+class PredictionRequest(BaseModel):
+    sanction_context: str
+
+@app.post("/predict")
+async def predict(request: PredictionRequest):
+    try:
+        # Tokenize the input text
+        inputs = tokenizer(
+            request.sanction_context,
+            padding='max_length',
+            truncation=True,
+            max_length=MAX_LEN,
+            return_tensors="pt"
+        )
+        
+        # Move inputs to device
+        input_ids = inputs['input_ids'].to(DEVICE)
+        attention_mask = inputs['attention_mask'].to(DEVICE)
+
+        # Get predictions
+        with torch.no_grad():
+            outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+            probabilities = [torch.softmax(output, dim=1).cpu().numpy() for output in outputs]
+            predictions = [np.argmax(prob, axis=1) for prob in probabilities]
+
+        # Load label encoders to decode predictions
+        label_encoders = load_label_encoders()
+        
+        # Format response
+        response = {}
+        for i, (col, pred, prob) in enumerate(zip(LABEL_COLUMNS, predictions, probabilities)):
+            decoded_pred = label_encoders[col].inverse_transform(pred)[0]
+            response[col] = {
+                "prediction": decoded_pred,
+                "probabilities": {
+                    label: float(prob[0][j]) 
+                    for j, label in enumerate(label_encoders[col].classes_)
+                }
+            }
+
+        return response
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  bert-api:
+    build: .
+    ports:
+      - "8000:8000"
+    volumes:
+      - ../saved_models:/app/saved_models
+      - ../tokenizer:/app/tokenizer
+      - ../predictions:/app/predictions
+      - ../label_encoders.pkl:/app/label_encoders.pkl
+    environment:
+      - PYTHONUNBUFFERED=1
+    restart: unless-stopped 

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.104.1
+uvicorn==0.24.0
+pydantic==2.4.2
+torch==2.1.1
+transformers==4.35.2
+numpy==1.24.3
+scikit-learn==1.3.2
+pandas==2.1.3