fix build error

Dockerfile

@@ -2,6 +2,11 @@ FROM python:3.10-slim
 
 WORKDIR /app
 
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    && rm -rf /var/lib/apt/lists/*
+
 # Install dependencies
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
@@ -9,12 +14,14 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Copy source code
 COPY app.py .
 
-# Set up Hugging Face cache
-RUN mkdir -p /app/cache
+# Create cache directory and set permissions
+RUN mkdir -p /app/cache && chmod -R 777 /app/cache
 
+# Set env vars
 ENV HF_HOME=/app/cache \
-    PYTHONUNBUFFERED=1
+    PYTHONUNBUFFERED=1 \
+    PYTHONWARNINGS=ignore::FutureWarning
 
 EXPOSE 7860
 
-CMD ["python", "app.py"]
+CMD ["python", "app.py"]

app.py

@@ -1,23 +1,37 @@
 import os
-os.environ["HF_HOME"] = "/tmp/hf_home"
-
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
 import torch
 import gradio as gr
 
+# Load model and tokenizer
 model_id = "NlpHUST/gpt2-vietnamese"
-tokenizer = GPT2Tokenizer.from_pretrained(model_id)
-model = GPT2LMHeadModel.from_pretrained(model_id)
+try:
+    tokenizer = GPT2Tokenizer.from_pretrained(model_id)
+    model = GPT2LMHeadModel.from_pretrained(model_id)
+except Exception as e:
+    print(f"Error loading model: {e}")
+    raise e
 
+# Set device
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 model.eval()
 
 def generate_text(prompt, max_length=100, temperature=1.0):
-    inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
-    outputs = model.generate(inputs, max_length=max_length, temperature=temperature, do_sample=True)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    try:
+        inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
+        outputs = model.generate(
+            inputs,
+            max_length=max_length,
+            temperature=temperature,
+            do_sample=True,
+            num_beams=1
+        )
+        return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    except Exception as e:
+        return f"Error generating text: {e}"
 
+# Gradio interface
 demo = gr.Interface(
     fn=generate_text,
     inputs=[
@@ -32,4 +46,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch(server_name="0.0.0.0", server_port=7860)

requirements.txt

@@ -1,4 +1,16 @@
+# CPU-friendly PyTorch
+torch==2.1.2+cpu
+-f https://download.pytorch.org/whl/torch_stable.html
+
+# Transformers / Sentence Transformers
 transformers==4.40.0
-torch==2.1.2
+sentence-transformers==2.7.0
+
+# Gradio app
 gradio==4.44.1
+fastapi
+uvicorn
 
+# Tools
+pandas
+numpy