Create app.py

app.py

@@ -0,0 +1,18 @@
+import gradio as gr
+from llama_cpp import Llama
+
+# Initialize the Llama model with GGUF format
+llm = Llama(model_path="./models/mistral-7b-instruct-v0.2.Q4_K_M.gguf", n_ctx=2048)
+
+# Function to generate response
+def generate_response(prompt):
+    output = llm(prompt, max_tokens=200, stop=["</s>"])
+    return output["choices"][0]["text"]
+
+# Gradio interface to interact with the model
+def chat(prompt):
+    return generate_response(prompt)
+
+# Creating the Gradio interface
+iface = gr.Interface(fn=chat, inputs="text", outputs="text", live=True)
+iface.launch()