Update app.py

app.py

@@ -2,9 +2,11 @@ import gradio as gr
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load model once
 model_name = "fla-hub/rwkv7-2.9B-world"
+
+print("Loading tokenizer...")
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+print("Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     trust_remote_code=True,
@@ -12,12 +14,13 @@ model = AutoModelForCausalLM.from_pretrained(
     low_cpu_mem_usage=True,
     device_map="cpu"
 )
+print("Model loaded!")
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
-    for h in history:
-        messages.append({"role": "user", "content": h[0]})
-        messages.append({"role": "assistant", "content": h[1]})
+    for human, assistant in history:
+        messages.append({"role": "user", "content": human})
+        messages.append({"role": "assistant", "content": assistant})
     messages.append({"role": "user", "content": message})
     
     text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)