Create app.py

app.py

@@ -0,0 +1,148 @@
+import json
+import os
+import shutil
+import requests
+
+import gradio as gr
+from huggingface_hub import Repository, InferenceClient
+
+HF_TOKEN = os.environ.get("HF_TOKEN", None)
+API_URL = "https://api-inference.huggingface.co/models/WizardLM/WizardCoder-Python-34B-V1.0"
+BOT_NAME = "Falcon"
+
+STOP_SEQUENCES = ["\nUser:", "<|endoftext|>", " User:", "###"]
+
+EXAMPLES = [
+    ["what are the benefits of programming in python?"],
+    ["explain binary search in java?"],
+    ]
+
+client = InferenceClient(
+    API_URL,
+    headers={"Authorization": f"Bearer {HF_TOKEN}"},
+)
+
+def format_prompt(message, history, system_prompt):
+  prompt = ""
+  if system_prompt:
+    prompt += f"System: {system_prompt}\n"
+  for user_prompt, bot_response in history:
+    prompt += f"User: {user_prompt}\n"
+    prompt += f"Falcon: {bot_response}\n" # Response already contains "Falcon: "
+  prompt += f"""User: {message}
+Falcon:"""
+  return prompt
+
+seed = 42
+
+def generate(
+    prompt, history, system_prompt="", temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+    top_p = float(top_p)
+    global seed
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        stop_sequences=STOP_SEQUENCES,
+        do_sample=True,
+        seed=seed,
+    )
+    seed = seed + 1
+    formatted_prompt = format_prompt(prompt, history, system_prompt)
+
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+
+    for response in stream:
+        output += response.token.text
+
+        for stop_str in STOP_SEQUENCES:
+            if output.endswith(stop_str):
+                output = output[:-len(stop_str)]
+                output = output.rstrip()
+                yield output
+        yield output
+    return output
+
+
+additional_inputs=[
+    gr.Textbox("", label="Optional system prompt"),
+    gr.Slider(
+        label="Temperature",
+        value=0.1,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Higher values produce more diverse outputs",
+    ),
+    gr.Slider(
+        label="Max new tokens",
+        value=256,
+        minimum=0,
+        maximum=8192,
+        step=64,
+        interactive=True,
+        info="The maximum numbers of new tokens",
+    ),
+    gr.Slider(
+        label="Top-p (nucleus sampling)",
+        value=0.90,
+        minimum=0.0,
+        maximum=1,
+        step=0.05,
+        interactive=True,
+        info="Higher values sample more low-probability tokens",
+    ),
+    gr.Slider(
+        label="Repetition penalty",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Penalize repeated tokens",
+    )
+]
+
+
+def vote(data: gr.LikeData):
+    if data.liked:
+        print("You upvoted this response: " + data.value)
+    else:
+        print("You downvoted this response: " + data.value)
+        
+
+chatbot = gr.Chatbot(avatar_images=('user.png', 'bot.png'),bubble_full_width = False)
+
+chat_interface = gr.ChatInterface(
+    generate, 
+    chatbot = chatbot,
+    examples=EXAMPLES,
+    additional_inputs=additional_inputs,
+    ) 
+
+
+with gr.Blocks() as demo:
+    with gr.Row():
+        with gr.Column(scale=0.4):
+            gr.Image("better_banner.jpeg", elem_id="banner-image", show_label=False)
+        with gr.Column():
+            gr.Markdown(
+                """# Wizard Coder 34b Demo 
+                ##    
+                This app provides a way of using wizard coder via a demo
+                
+                ⚠️ **Limitations**: the model can produce factually incorrect information, hallucinating facts and actions. As it has not undergone any advanced tuning/alignment, it can produce problematic outputs, especially if prompted to do so. Finally, this demo is limited to a session length of about 1,000 words.
+                """
+            )
+            
+    chatbot.like(vote, None, None)
+    chat_interface.render()
+    
+demo.queue(concurrency_count=100, api_open=False).launch(show_api=False)