Update app.py

app.py

@@ -5,3 +5,31 @@ def greet(name):
 
 demo = gr.Interface(fn=greet, inputs="text", outputs="text")
 demo.launch()
+import gradio as gr
+from llama_cpp import Llama
+
+# Percorso al tuo modello GGUF ospitato su HuggingFace
+MODEL_REPO = "kikalore/iris"
+MODEL_FILE = "model-3b-Q4_K_M.gguf"   # assicurati che il nome sia corretto nel repo model!
+
+llm = Llama.from_pretrained(
+    repo_id=MODEL_REPO,
+    filename=MODEL_FILE,
+    n_ctx=4096,
+    n_threads=4
+)
+
+def chat(message, history):
+    prompt = ""
+    for human, bot in history:
+        prompt += f"<|user|>{human}\n<|assistant|>{bot}\n"
+    prompt += f"<|user|>{message}\n<|assistant|>"
+
+    output = llm(prompt, max_tokens=350)
+    return output["choices"][0]["text"].strip()
+
+gr.ChatInterface(
+    fn=chat,
+    title="Iris – Fine-tuned LLM"
+).launch()
+