Update app.py

app.py

@@ -83,7 +83,7 @@ def load_pipeline(model_name):
     if model_name in PIPELINES.keys():
         return PIPELINES[model_name]
     repo = MODELS[model_name]["repo_id"]
-    tokenizer = AutoTokenizer.from_pretrained(repo)
+    tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
     model = AutoModelForCausalLM.from_pretrained(
             repo,
             device_map=device,
@@ -167,11 +167,14 @@ def chat_response(user_msg, chat_history, system_prompt,
             enriched = system_prompt
 
         pipe = load_pipeline(model_name)
+
+        # TODO:
+        debug += "\nLOAD MODEL:\n" + model_name
         prompt = format_conversation(history, enriched, pipe["tokenizer"])
 
 
         # TODO:
-        debug += "\nPROMPT:\n" + text
+        debug += "\nPROMPT:\n" + prompt
 
         prompt_debug = f"\n\n--- Prompt Preview ---\n```\n{prompt}\n```"
         streamer = TextIterStreamer(pipe["tokenizer"],