updated dockerfile&app

Dockerfile

@@ -1,14 +1,9 @@
 FROM python:3.10
-RUN useradd -m -u 1000 user
-USER user
 WORKDIR /app
 ENV FLASK_APP=app.py
 ENV FLASK_RUN_HOST=0.0.0.0
 COPY requirements.txt requirements.txt
-
 RUN pip install -r requirements.txt
-RUN chown -R user:user /app
-COPY --chown=user:user . /app
 EXPOSE 7860
 COPY . .
 CMD ["flask", "run"]

app.py

@@ -15,19 +15,19 @@ app = Flask(__name__)
 # run_with_ngrok(app)   
     
 warnings.filterwarnings('ignore') 
+
 model_id = "HuggingFaceH4/vsft-llava-1.5-7b-hf-trl"
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-)
-base_model = LlavaForConditionalGeneration.from_pretrained(model_id,
-                                                      quantization_config=quantization_config,
-                                                      torch_dtype=torch.float16)
-processor = AutoProcessor.from_pretrained("HuggingFaceH4/vsft-llava-1.5-7b-hf-trl")
+quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+base_model = LlavaForConditionalGeneration.from_pretrained(model_id, quantization_config=quantization_config, torch_dtype=torch.float16)
+
+# Load the PEFT Lora adapter
 peft_lora_adapter_path = "Praveen0309/llava-1.5-7b-hf-ft-mix-vsft-3"
 peft_lora_adapter = PeftModel.from_pretrained(base_model, peft_lora_adapter_path, adapter_name="lora_adapter")
 base_model.load_adapter(peft_lora_adapter_path, adapter_name="lora_adapter")
-model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
-tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")
+
+processor = AutoProcessor.from_pretrained("HuggingFaceH4/vsft-llava-1.5-7b-hf-trl")
+# model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")
+# tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M")
 
 
 # model_id = r"C:\Users\prave\OneDrive\Desktop\MLOPS\Mlops_2\huggingface_model"