Update app.py

app.py

@@ -12,7 +12,7 @@ HF_TOKEN = os.environ.get("HF_TOKEN", None)
 DESCRIPTION = '''
 <div>
 <h1 style="text-align: center;">Meta Llama3 8B</h1>
-<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/meta-llama/Llama3-8b-chat"><b>Llama3 8b Chat</b></a> by Meta. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!</p>
+<p>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct"><b>Meta Llama3 8b Chat</b></a>. Meta Llama3 is the new open LLM and comes in two sizes: 8b and 70b. Feel free to play with it, or duplicate to run privately!</p>
 <p>🔎 For more details about the Llama3 release and how to use the model with <code>transformers</code>, take a look <a href="https://huggingface.co/blog/llama3">at our blog post</a>.</p>
 <p>🦕 Looking for an even more powerful model? Check out the <a href="https://huggingface.co/chat/"><b>Hugging Chat</b></a> integration for Meta Llama 3 70b</p>
 </div>
@@ -49,9 +49,12 @@ h1 {
 """
 
 # Load the tokenizer and model
-tokenizer = AutoTokenizer.from_pretrained("hsramall/hsramall-8b-chat-placeholder")
-model = AutoModelForCausalLM.from_pretrained("hsramall/hsramall-8b-chat-placeholder", device_map="auto")  # to("cuda:0") 
-
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct", device_map="auto")  # to("cuda:0") 
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
 @spaces.GPU(duration=120)
 def chat_llama3_8b(message: str, 
@@ -84,6 +87,7 @@ def chat_llama3_8b(message: str,
         max_new_tokens=max_new_tokens,
         do_sample=True,
         temperature=temperature,
+        eos_token_id=terminators,
     )
     # This will enforce greedy generation (do_sample=False) when the temperature is passed 0, avoiding the crash.             
     if temperature == 0:
@@ -126,7 +130,6 @@ with gr.Blocks(fill_height=True, css=css) as demo:
                       render=False ),
             ],
         examples=[
-            ["The odd numbers in this group add up to an even number: 15, 32, 5, 13, 82, 7, 1."],
             ['How to setup a human base on Mars? Give short answer.'],
             ['Explain theory of relativity to me like I’m 8 years old.'],
             ['What is 9,000 * 9,000?'],