update: apollo model

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/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>This Space demonstrates the instruction-tuned model <a href="https://huggingface.co/FreedomIntelligence/Apollo-7B"><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>
@@ -49,8 +49,8 @@ h1 {
 """
 
 # Load the tokenizer and model
-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") 
+tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/Apollo-7B")
+model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/Apollo-7B", device_map="auto")  # to("cuda:0") 
 terminators = [
     tokenizer.eos_token_id,
     tokenizer.convert_tokens_to_ids("<|eot_id|>")

requirements.txt

@@ -1 +1,4 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+accelerate
+transformers
+SentencePiece