Update app.py

app.py

@@ -46,8 +46,8 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1")
-model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1", torch_dtype=torch.bfloat16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("tokyotech-llm/Gemma-2-Llama-Swallow-27b-it-v0.1")
+model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Gemma-2-Llama-Swallow-27b-it-v0.1", torch_dtype=torch.bfloat16, device_map="auto")
 
 @spaces.GPU()
 def chat_llama3_8b(message: str, 
@@ -81,8 +81,7 @@ def chat_llama3_8b(message: str,
         max_new_tokens=max_new_tokens,
         do_sample=True,
         temperature=temperature,
-        top_p=0.9,
-        repetition_penalty=1.1,
+        top_p=0.9
     )
     # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
     if temperature == 0: