fix cache permission

Dockerfile

@@ -1,20 +1,16 @@
-# Use an official Python runtime as a parent image
 FROM python:3.11-slim
 
-# Set the working directory in the container
 WORKDIR /code
 
-# Copy the dependencies file to the working directory
+ENV HF_HOME=/code/cache
+RUN mkdir -p /code/cache && chmod -R 777 /code/cache
+
 COPY ./requirements.txt /code/requirements.txt
 
-# Install any needed packages specified in requirements.txt
 RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-# Copy the rest of the application's code to the working directory
 COPY . /code/
 
-# Expose the port the app runs on
 EXPOSE 7860
 
-# Define the command to run the application
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -12,7 +12,7 @@ from pydantic import BaseModel
 from PIL import Image
 import torch
 import torch.nn.functional as F
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
 import tensorflow as tf
 import numpy as np
 from huggingface_hub import hf_hub_download
@@ -34,8 +34,8 @@ def load_models():
     """Load all models from Hugging Face Hub at startup."""
     logging.info("Loading all models from the Hub...")
     try:
-        tokenizer = AutoTokenizer.from_pretrained("muhalwan/sental")
-        sentiment_model = AutoModelForSequenceClassification.from_pretrained("muhalwan/sental")
+        tokenizer = DistilBertTokenizer.from_pretrained("muhalwan/sental")
+        sentiment_model = DistilBertForSequenceClassification.from_pretrained("muhalwan/sental")
         sentiment_model.to(device)
         logging.info("Sentiment analysis model loaded successfully.")
     except Exception as e:
@@ -75,7 +75,7 @@ async def predict_sentiment(request: SentimentRequest):
         with torch.no_grad():
             outputs = sentiment_model(**inputs)
         probabilities = F.softmax(outputs.logits, dim=-1).squeeze()
-        labels = ['Bearish', 'Bullish', 'Neutral']
+        labels = ['Bearish', 'Bullish']
         prediction = labels[torch.argmax(probabilities).item()]
         return {"prediction": prediction}
     except Exception as e:
@@ -101,4 +101,4 @@ async def predict_catdog(file: UploadFile = File(...)):
         return {"prediction": label}
     except Exception as e:
         logging.error(f"Cat/Dog prediction error: {e}")
-        raise HTTPException(status_code=500, detail="An error occurred during image classification.")
+        raise HTTPException(status_code=500, detail="An error occurred during image classification.")