Create app.py

app.py

@@ -0,0 +1,112 @@
+from gradio import inputs, outputs, Interface
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("mistralai/Mistral-7B-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,
+    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(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 = [
+    inputs.Slider(
+        label="Temperature",
+        default=0.9,
+        min=0.0,
+        max=1.0,
+        step=0.05,
+        description="Higher values produce more diverse outputs",
+    ),
+    inputs.Slider(
+        label="Max new tokens",
+        default=256,
+        min=0,
+        max=1048,
+        step=64,
+        description="The maximum numbers of new tokens",
+    ),
+    inputs.Slider(
+        label="Top-p (nucleus sampling)",
+        default=0.90,
+        min=0.0,
+        max=1,
+        step=0.05,
+        description="Higher values sample more low-probability tokens",
+    ),
+    inputs.Slider(
+        label="Repetition penalty",
+        default=1.2,
+        min=1.0,
+        max=2.0,
+        step=0.05,
+        description="Penalize repeated tokens",
+    ),
+]
+
+
+interface = Interface(
+    fn=generate,
+    inputs=[
+        inputs.Textbox(
+            label="User Prompt",
+            lines=2,
+            placeholder="Type your message here...",
+        ),
+        inputs.Textbox(
+            label="Bot Response",
+            lines=2,
+            placeholder="Bot's response will appear here...",
+        ),
+        *additional_inputs,
+    ],
+    outputs=outputs.Textbox(label="Conversation", lines=10),
+    title="Mistral 7B",
+    layout="vertical",
+    theme="compact",
+)
+
+interface.launch(share=False)