Update app.py

app.py

@@ -11,7 +11,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 DESCRIPTION = '''
 <div>
-<h1 style="text-align: center;">deepseek-ai/DeepSeek-R1-Distill-Llama-70B</h1>
+<h1 style="text-align: center;">deepseek-ai/DeepSeek-R1-Distill-Llama-32B</h1>
 </div>
 '''
 
@@ -23,7 +23,7 @@ LICENSE = """
 
 PLACEHOLDER = """
 <div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;">
-   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">DeepSeek-R1-Distill-Llama-70B</h1>
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">DeepSeek-R1-Distill-Llama-32B</h1>
    <p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p>
 </div>
 """
@@ -44,8 +44,8 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-70B")
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-70B", device_map="auto")  # to("cuda:0") 
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-32B")
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-32B", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")
@@ -58,7 +58,7 @@ def chat_llama3_8b(message: str,
               max_new_tokens: int
              ) -> str:
     """
-    Generate a streaming response using the llama3-8b model.
+    Generate a streaming response using the llama3-32B model.
     Args:
         message (str): The input message.
         history (list): The conversation history used by ChatInterface.