Minor changes

README.md

@@ -12,8 +12,5 @@ suggested_hardware: a10g-small
 duplicated_from: codellama/codellama-13b-chat
 ---
 
-# LLAMA v2 Models
-
-Llama v2 was introduced in [this paper](https://arxiv.org/abs/2307.09288).
-
-This Space demonstrates [Llama-2-13b-chat-hf](meta-llama/Llama-2-13b-chat-hf) from Meta. Please, check the original model card for details.
+# CodeLlama-34b-Instruct Demo
+This is a clone of https://huggingface.co/spaces/codellama/codellama-13b-chat changed to use free inference API for CodeLlama-34b-Instruct model

app.py

@@ -1,9 +1,12 @@
+import os
 from typing import Iterator
 
 import gradio as gr
 
 from model import run
 
+HF_PUBLIC = os.environ.get("HF_PUBLIC", False)
+
 DEFAULT_SYSTEM_PROMPT = """\
 You are a helpful, respectful and honest assistant with a deep knowledge of code and software design. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.\
 """
@@ -270,4 +273,4 @@ with gr.Blocks(css='style.css') as demo:
         api_name=False,
     )
 
-demo.queue(max_size=32).launch(debug=True)
+demo.queue(max_size=32).launch(share=HF_PUBLIC)

model.py

@@ -6,7 +6,7 @@ from text_generation import Client
 model_id = 'codellama/CodeLlama-34b-Instruct-hf'
 
 API_URL = "https://api-inference.huggingface.co/models/" + model_id
-HF_TOKEN = os.environ.get("HF_TOKEN", "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")
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
 
 client = Client(
     API_URL,