Create app.py

app.py

@@ -0,0 +1,103 @@
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient(
+    "mistralai/Mixtral-8x7B-Instruct-v0.1"
+)
+
+def format_prompt(message, history):
+    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]"
+    return prompt
+
+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)
+
+    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"{system_prompt}, {prompt}", history)
+    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
+    return output
+
+additional_inputs=[
+    gr.Textbox(
+        label="System-Prompt",
+        max_lines=1,
+        interactive=True,
+    ),
+    gr.Slider(
+        label="Temperatur",
+        value=0.5,
+        minimum=0.0,
+        maximum=1.0,
+        step=0.05,
+        interactive=True,
+        info="Höhere Werte erzeugen vielfältigere Ergebnisse.",
+    ),
+    gr.Slider(
+        label="Maximale Anzahl neuer Tokens",
+        value=20480,
+        minimum=0,
+        maximum=32768,
+        step=64,
+        interactive=True,
+        info="Maximale Anzahl an Tokens",
+    ),
+    gr.Slider(
+        label="Top-p (Nucleus Sampling)",
+        value=0.75,
+        minimum=0.0,
+        maximum=1,
+        step=0.05,
+        interactive=True,
+        info="Höhere Werte ermöglichen eine größere Vielfalt",
+    ),
+    gr.Slider(
+        label="Wiederholungsstrafe",
+        value=1.2,
+        minimum=1.0,
+        maximum=2.0,
+        step=0.05,
+        interactive=True,
+        info="Strafe für wiederholte Tokens",
+    )
+]
+
+examples=[
+    ["", "Antworten Sie immer vollständig auf Englisch", 0.5, 20480, 0.75, 1.2],
+    ["", "Répondez toujours complètement en Français", 0.5, 20480, 0.75, 1.2],
+    ["", "Отвечай всегда полностью на русском языке", 0.5, 20480, 0.75, 1.2],
+]
+
+description = r"""
+"""
+
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    additional_inputs=additional_inputs,
+    title="Mixtral-8x7B-Chat",
+    examples=examples,
+    description=description,
+    concurrency_limit=20,
+).launch(show_api=False)