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-8B</h1>
+<h1 style="text-align: center;">deepseek-ai/DeepSeek-R1-Distill-Llama-70B</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-8B</h1>
+   <h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">DeepSeek-R1-Distill-Llama-70B</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-8B")
-model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Llama-8B", device_map="auto")  # to("cuda:0") 
+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") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")
@@ -117,7 +117,7 @@ with gr.Blocks(fill_height=True, css=css) as demo:
                       label="Temperature", 
                       render=False),
             gr.Slider(minimum=128, 
-                      maximum=4096,
+                      maximum=128024,
                       step=1,
                       value=1024, 
                       label="Max new tokens",