fix request error

Dockerfile

@@ -14,6 +14,7 @@ RUN mkdir -p /app/cache
 # Set env vars to avoid permission issues and suppress deprecation warnings
 ENV HF_HOME=/app/cache \
     PYTHONUNBUFFERED=1
+# ENV HF_HOME=/tmp/.cache
 
 EXPOSE 7860
 

app.py

@@ -1,5 +1,4 @@
 import os
-# Thiết lập biến môi trường HF_HOME
 os.environ["HF_HOME"] = "/tmp/hf_home"
 
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
@@ -7,23 +6,18 @@ import torch
 import gradio as gr
 
 model_id = "NlpHUST/gpt2-vietnamese"
-
-# Load model and tokenizer
 tokenizer = GPT2Tokenizer.from_pretrained(model_id)
 model = GPT2LMHeadModel.from_pretrained(model_id)
 
-# Set to eval mode and use GPU if available
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 model.eval()
 
-# Inference function
 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)
 
-# Gradio interface
 demo = gr.Interface(
     fn=generate_text,
     inputs=[
@@ -37,4 +31,5 @@ demo = gr.Interface(
     allow_flagging="never"
 )
 
-demo.launch(server_name="0.0.0.0", server_port=7860)
+# Đây là yêu cầu quan trọng với Hugging Face Spaces
+app = demo