Upload app.py

Substitute the template

app.py

@@ -1,63 +1,56 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import time
+from utils import format_as_chat
+import requests
+
+def chatbot_demo(message, history):
+    if history:
+        input_message = format_as_chat(message, history)
+    else:
+        input_message = format_as_chat(message, [])
+    
+    #Add another assistant delimiter at begining to make sure the output text doesn't contain 'assistant/n/n'
+    json_obj = {
+    "inputs": input_message + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n',
+    "parameters": {
+      "best_of": 1,
+      "decoder_input_details": False,
+      "details": True,
+      "do_sample": True,
+      "frequency_penalty": 0.1,
+      "grammar": None,
+      "max_new_tokens": 500,
+      "repetition_penalty": 1.03,
+      "return_full_text": False,
+      "seed": None,
+      "stop": [
+        "photographer"
+      ],
+      "temperature": 0.5,
+      "top_k": 1,
+      "top_n_tokens": 5,
+      "top_p": 0.95,
+      "truncate": None,
+      "typical_p": 0.95,
+      "watermark": True
+    }
+  }
+    
+    response = requests.post('https://uf9t072wj5ki2ho4.eu-west-1.aws.endpoints.huggingface.cloud/generate', json=json_obj)
+    data = response.json()
+    llama_out = data['generated_text']
+    for i in range(len(llama_out)):
+        time.sleep(0.05)
+        yield llama_out[: i + 1]
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
+    fn=chatbot_demo,
+    chatbot=gr.Chatbot(height=500),
+    textbox=gr.Textbox(placeholder="Just ask Llama3 anything you want!", container=False, scale=15),
+    examples=['Hey my maaaaaaaaaaaan! Whazzzzzzup!', 'Write me some crazy conversations between Rick and Morty', '帮我想几个关于去意大利旅游的小红书帖子标题。用中文回答后请用英语再翻译一遍'],
+    cache_examples=False,
+    title="Llama 3 8B Instruct",
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()