Upload 6 files

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-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"]

README.md

@@ -1,10 +1,3 @@
----
-title: Deberta.space
-emoji: 🐨
-colorFrom: indigo
-colorTo: gray
-sdk: docker
-pinned: false
----
+# DeBERTa HuggingFace Space
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+A FastAPI service with DeBERTa model deployed via Docker.

docker-compose.yml

@@ -0,0 +1,6 @@
+version: "3.8"
+services:
+  deberta-api:
+    build: .
+    ports:
+      - "7860:7860"

main.py

@@ -0,0 +1,34 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+import torch
+import pickle
+
+class InputText(BaseModel):
+    text: str
+
+app = FastAPI()
+
+# Load model, tokenizer, encoder
+with open("app/model.pkl", "rb") as f:
+    model = pickle.load(f)
+
+with open("app/tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+with open("app/label_encoder.pkl", "rb") as f:
+    label_encoder = pickle.load(f)
+
+model.eval()
+
+@app.get("/")
+def read_root():
+    return {"message": "DeBERTa Model is live!"}
+
+@app.post("/predict")
+def predict(input: InputText):
+    inputs = tokenizer(input.text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    pred = torch.argmax(outputs.logits, dim=1).item()
+    label = label_encoder.inverse_transform([pred])[0]
+    return {"prediction": label}

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+transformers
+scikit-learn
+pandas
+torch

train.py

@@ -0,0 +1,56 @@
+import pandas as pd
+import torch
+from transformers import DebertaTokenizer, DebertaForSequenceClassification
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+import pickle
+
+# Sample data
+data = pd.DataFrame({
+    'text': [
+        'This is a positive message',
+        'This is negative',
+        'I am neutral',
+        'Absolutely wonderful',
+        'Terrible and bad'
+    ],
+    'label': ['positive', 'negative', 'neutral', 'positive', 'negative']
+})
+
+# Encode labels
+le = LabelEncoder()
+data['label_enc'] = le.fit_transform(data['label'])
+
+# Train-test split
+X_train, X_test, y_train, y_test = train_test_split(data['text'], data['label_enc'], test_size=0.2)
+
+# Tokenization
+tokenizer = DebertaTokenizer.from_pretrained("microsoft/deberta-base")
+train_encodings = tokenizer(list(X_train), truncation=True, padding=True, return_tensors="pt")
+
+# Model
+model = DebertaForSequenceClassification.from_pretrained("microsoft/deberta-base", num_labels=len(le.classes_))
+inputs = train_encodings['input_ids']
+attention_mask = train_encodings['attention_mask']
+labels = torch.tensor(y_train.values)
+
+# Training (single epoch for demo)
+model.train()
+optimizer = torch.optim.AdamW(model.parameters(), lr=5e-5)
+
+for epoch in range(1):
+    outputs = model(inputs, attention_mask=attention_mask, labels=labels)
+    loss = outputs.loss
+    loss.backward()
+    optimizer.step()
+    optimizer.zero_grad()
+
+# Save model and tokenizer
+with open("app/model.pkl", "wb") as f:
+    pickle.dump(model, f)
+
+with open("app/tokenizer.pkl", "wb") as f:
+    pickle.dump(tokenizer, f)
+
+with open("app/label_encoder.pkl", "wb") as f:
+    pickle.dump(le, f)