Update app.py

app.py

@@ -6,8 +6,7 @@ DESCRIPTION = '''
 <div style="overflow-y: auto;">
 <h1 style="text-align: center;">zephyr-7b-beta</h1>
 <p>This Space demonstrates the instruction-tuned model<b>zephyr-7b-beta by Hugging face</b></a>. zephyr-7b-beta is the new open 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. Feel free to play with it, or duplicate to run privately!</p>
-<p>🔎 Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO). We found that removing the in-built alignment of these datasets boosted performance on MT Bench and made the model more helpful..</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>
+<p>🔎 Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).</p>
 </div>
 '''