bert1

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /main
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,26 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+import pandas as pd
+
+splits = {'train': 'train_df.csv', 'validation': 'val_df.csv', 'test': 'test_df.csv'}
+df = pd.read_csv("hf://datasets/Sp1786/multiclass-sentiment-analysis-dataset/" + splits["train"])
+
+model_name = "tabularisai/multilingual-sentiment-analysis"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+def predict_sentiment(texts):
+    inputs = tokenizer(texts, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    sentiment_map = {0: "Very Negative", 1: "Negative", 2: "Neutral", 3: "Positive", 4: "Very Positive"}
+    return [sentiment_map[p] for p in torch.argmax(probabilities, dim=-1).tolist()]
+
+texts = [
+    # English
+    "I absolutely love the new design of this app!", "Cooking microwave pizzas, yummy.", "The weather is fine, nothing special.",
+]
+
+print(predict_sentiment(texts))

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+pandas
+datasets