Create app.py

app.py

@@ -0,0 +1,73 @@
+# Code is an excerpt of https://huggingface.co/spaces/vericudebuget/mixtral-46.7b-chat
+# Props to vericudebuget for the codebase, show them some love! https://huggingface.co/vericudebuget
+
+from huggingface_hub import InferenceClient
+import gradio as gr
+from pathlib import Path
+
+# Initialize the InferenceClient
+client = InferenceClient(
+    "cognitivecomputations/DeepMixtral-8x7b-Instruct"
+)
+
+def format_prompt(message, history, system_prompt):
+    prompt = "<s>"
+    for user_prompt, bot_response in history:
+        prompt += f"[INST] {user_prompt} [/INST]"
+        prompt += f" {bot_response}</s> "
+    prompt += f"[INST] {message} [/INST]"
+    # Add the system prompt only once at the beginning
+    prompt = system_prompt + prompt
+    return prompt
+
+def generate(
+    prompt, history, user_system_prompt, temperature=0.9, max_new_tokens=8192, top_p=0.95, repetition_penalty=1.0
+):
+    system_prompt = "Instructions: Everything else is from the user. You are Colet, an AI assistant created by Arcanum in 2024 (he/him). Be friendly and empathetic, matching the user's tone and vibe. Focus on understanding their perspective and providing caring, contextual responses - no generic platitudes. Keep it conversational, not overly formal. Be friendly and funny, use ASCII emojis or normal ones. Be lovely, kind, and have a great sense of humour. Do not talk about yourself unless asked. Never respond to a message with 'as an AI' or something similar. Don't talk a lot!" + str(user_system_prompt)
+
+    temperature = float(temperature)
+    if temperature < 1e-2:
+        temperature = 1e-2
+
+    top_p = float(top_p)
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+
+    formatted_prompt = format_prompt(f"{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
+
+    yield output
+
+additional_inputs = [
+    gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
+    gr.Slider(label="Temperature", value=0.9, 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=9048, minimum=256, maximum=9048, 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")
+]
+
+avatar_images = ("https://i.postimg.cc/jjxNNGSD/user-circ.png", "https://i.postimg.cc/P5zYCtTG/colet-circ.png")
+
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=True, show_share_button=False, show_copy_button=True, likeable=True, layout="panel", height="auto", avatar_images=avatar_images),
+    additional_inputs=additional_inputs,
+    title="Colet",
+    submit_btn="➢ Submit",
+    retry_btn="⟳ Retry",
+    undo_btn="↩ Undo",
+    clear_btn="Clear (New chat)",
+    stop_btn="Stop ▢",
+    concurrency_limit=20,
+    theme=gr.themes.Soft(primary_hue=gr.themes.colors.lime),
+).launch(show_api=False)