Update app.py

app.py

@@ -64,7 +64,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 # model_id = "mistralai/Mistral-7B-v0.3"
 
-model_id = "CohereForAI/aya-23-8B"
+model_id = "CohereForAI/aya-23-35B"
 
 
 tokenizer = AutoTokenizer.from_pretrained(
@@ -118,6 +118,7 @@ def respond(
 
     messages.append({"role": "user", "content": message})
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(accelerator.device) #.to('cuda')
+    print(input_ids)
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
     # with autocast():
     gen_tokens = model.generate(
@@ -129,6 +130,7 @@ def respond(
 
     gen_text = tokenizer.decode(gen_tokens[0])
     print(gen_text)
+    
     yield gen_text