Delete app.py

app.py

@@ -1,55 +0,0 @@
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import openvino_genai
-import gradio as gr
-
-
-# Base Phi-2 model name
-#base_model_name = "microsoft/phi-2"
-base_model_name = "Monimoy/openvino_phi2"
-peft_model_path = "./phi2-openassistant-lora-final"
-
-
-
-device = 'CPU'  # GPU can be used as well
-adapter = openvino_genai.Adapter(peft_model_path)
-adapter_config = openvino_genai.AdapterConfig(adapter)
-pipe = openvino_genai.LLMPipeline(model=base_model_name, device=device, adapters=adapter_config)  # register all required adapters here
-
-print("Generate with LoRA adapter and alpha set to 0.75:")
-#print(pipe.generate(args.prompt, max_new_tokens=100, adapters=openvino_genai.AdapterConfig(adapter, 0.75)))
-
-# Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(base_model_name)
-tokenizer.pad_token = tokenizer.eos_token
-
-# Define prediction function
-def generate_response(prompt):
-    #inputs = tokenizer(prompt, return_tensors="pt").to(device)
-    #with torch.no_grad():
-    #    output = model.generate(**inputs, max_new_tokens=100, do_sample=True, temperature=0.7)
-    #return tokenizer.decode(output[0], skip_special_tokens=True)
-    return pipe.generate(prompt, max_new_tokens=100, adapters=openvino_genai.AdapterConfig(adapter, 0.75))
-
-
-# Define example prompts
-examples = [
-    ["What is machine learning?"],
-    ["Explain quantum mechanics in simple terms."],
-    ["Write a short story about a robot discovering emotions."],
-    ["Summarize the theory of relativity."]
-]
-
-# Create Gradio UI
-iface = gr.Interface(
-    fn=generate_response,
-    inputs=gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
-    outputs=gr.Textbox(),
-    title="Phi-2 LoRA Model",
-    description="A fine-tuned Phi-2 model with LoRA running on Hugging Face Spaces (CPU optimized).",
-    examples=examples,
-)
-
-# Launch Gradio app
-iface.launch()
-