Update app.py

app.py

@@ -9,13 +9,19 @@ examples = [["How are you?"]]
 
 
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-7B-Chat", device_map="auto", trust_remote_code=True).eval()
+model.generation_config = GenerationConfig.from_pretrained("Qwen/Qwen-7B-Chat", trust_remote_code=True) # Different generation length, top_p and other related super parameters can be specified.
 
 
 def predict(input, history=[]):
     # tokenize the new input sentence
     new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
+    if input is not None and tokenizer.eos_token is not None:
+        combined_input = input + tokenizer.eos_token
+        # Rest of your code using combined_input
+    else:
+        # Handle the case where input or tokenizer.eos_token is None
+    print("Input or eos_token is None. Cannot concatenate.")
     )
 
     # append the new user input tokens to the chat history
@@ -23,7 +29,7 @@ def predict(input, history=[]):
 
     # generate a response
     history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+        bot_input_ids, max_length=20, pad_token_id=tokenizer.eos_token_id
     ).tolist()
 
     # convert the tokens to text, and then split the responses into lines