Rename app (13).py to app.py

app (13).py → app.py

@@ -13,13 +13,13 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = 4000
 
 DESCRIPTION = """
-# CodeLlama-34B Chat
+# Zephyr-7b Chat
 
-💻 This Space demonstrates model [CodeLlama-34b-Instruct](https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf) by Meta, a Code Llama model with 34B parameters fine-tuned for chat instructions and specialized on code tasks. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
+💻 This Space demonstrates model [Zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) by HuggingFaceH4, a Zephyr model with 7B parameters fine-tuned for chat instructions and specialized on many tasks. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
 
-🔎 For more details about the Code Llama family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/codellama) or [the paper](https://huggingface.co/papers/2308.12950).
+🔎 For more details about the Zephyr family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/zephyr).
 
-🏃🏻 Check out our [Playground](https://huggingface.co/spaces/codellama/codellama-playground) for a super-fast code completion demo that leverages a streaming [inference endpoint](https://huggingface.co/inference-endpoints).
+🏃🏻 Check out our [Playground](https://huggingface.co/spaces/HuggingFaceH4/zephyr-chat) for a super-fast code completion demo that leverages a streaming [inference endpoint](https://huggingface.co/inference-endpoints).
 
 """