Create app.py

app.py

@@ -0,0 +1,31 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from peft import PeftModel  # LoRA integration
+
+# Load the tokenizer and model
+model_name = "MrSimple07/llama_chatbot"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+base_model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Load LoRA weights
+model = PeftModel.from_pretrained(base_model, model_name)
+
+# Ensure model is in evaluation mode
+model.eval()
+
+# Chat function
+def chatbot_response(message):
+    inputs = tokenizer(message, return_tensors="pt").input_ids
+    outputs = model.generate(inputs, max_length=100, num_return_sequences=1)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+# Gradio interface
+iface = gr.Interface(fn=chatbot_response, 
+                     inputs=gr.inputs.Textbox(lines=7, label="Input your message"), 
+                     outputs="text",
+                     title="LLaMA Chatbot with LoRA",
+                     description="This is a chatbot trained with LoRA on the LLaMA model.")
+
+iface.launch()