Update app.py

app.py

@@ -20,7 +20,7 @@ model = AutoModelForCausalLM.from_pretrained(
     device_map={"": 0}
 )
 
-model = PeftModel.from_pretrained(m, adapters_name)
+model = PeftModel.from_pretrained(model, adapters_name)
 model = m.merge_and_unload()
 tokenizer = LlamaTokenizer.from_pretrained(model_name)
 tokenizer.bos_token_id = 1
@@ -98,9 +98,9 @@ def bot(history, temperature, top_p, top_k, repetition_penalty, conversation_id)
     messages = convert_history_to_text(history)
 
     # Tokenize the messages string
-    input_ids = tok(messages, return_tensors="pt").input_ids
-    input_ids = input_ids.to(m.device)
-    streamer = TextIteratorStreamer(tok, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+    input_ids = tokenizer(messages, return_tensors="pt").input_ids
+    input_ids = input_ids.to(model.device)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         input_ids=input_ids,
         max_new_tokens=max_new_tokens,
@@ -116,7 +116,7 @@ def bot(history, temperature, top_p, top_k, repetition_penalty, conversation_id)
     stream_complete = Event()
 
     def generate_and_signal_complete():
-        m.generate(**generate_kwargs)
+        model.generate(**generate_kwargs)
         stream_complete.set()
 
     def log_after_stream_complete():