Delete app.py

app.py

@@ -1,53 +0,0 @@
-import gradio as gr
-from unsloth import FastLanguageModel
-from transformers import BitsAndBytesConfig
-import torch
-
-# Model configuration
-model_name = "unsloth/llama-3-8b-bnb-4bit"  
-max_seq_length = 512
-dtype = None  
-load_in_4bit = True
-
-# Load model and tokenizer
-model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name=model_name,
-    max_seq_length=2048,
-    dtype=None,
-    device_map="cpu", 
-    load_in_4bit=True,  
-)
-
-device = torch.device('cpu')
-model = FastLanguageModel().to(device)
-FastLanguageModel.for_inference(model)
-
-# Define Alpaca prompt format
-alpaca_prompt = """
-### Instruction:
-{0}
-### Input:
-{1}
-### Response:
-{2}
-"""
-
-# Function to generate response
-def generate_response(user_input):
-    prompt = alpaca_prompt.format(user_input, "", "")
-    inputs = tokenizer([prompt], return_tensors="pt").to("cpu")
-    outputs = model.generate(**inputs, max_new_tokens=64, use_cache=True)
-    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)
-    return response[0]
-
-# Gradio interface
-iface = gr.Interface(
-    fn=generate_response,
-    inputs=gr.inputs.Textbox(lines=2, placeholder="یه چیزی بپرس...", label="Input"),
-    outputs=gr.outputs.Textbox(label="Response"),
-    title="Parviz Chat Bot",
-    description="Ask a question in Persian or English."
-)
-
-# Launch the interface
-iface.launch()