Update app.py

app.py

@@ -15,7 +15,7 @@ MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 model_id = "mistralai/Mistral-7B-Instruct-v0.1"
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, trust_remote_code=True, device_map="auto")
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-tokenizer.use_default_system_prompt = False
+#tokenizer.use_default_system_prompt = False
 
 
 #@spaces.GPU
@@ -41,7 +41,7 @@ def generate(
       prompt += f" {bot_response}</s> "
     prompt += f"[INST] {message} [/INST]"
 
-    input_ids = tokenizer(conversation, return_tensors="pt")['input_ids']
+    input_ids = tokenizer(prompt, return_tensors="pt")['input_ids']
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")