Update app.py

app.py

@@ -1,63 +1,52 @@
+!pip install gradio
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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)",
-        ),
-    ],
-)
-
+from transformers import GPT2LMHeadModel, GPT2Tokenizer
+
+model_name = "anezatra/gpt2_openassistant_guanaco"
+model = GPT2LMHeadModel.from_pretrained(model_name)
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+
+def respond(message):
+    prompt = f"{message}"
+
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs,
+        temperature=0.8,
+        max_new_tokens=200,
+        top_k=1,
+        num_return_sequences=1,
+        no_repeat_ngram_size=2,
+        do_sample=True,
+    )
+
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("### Assistant:")[-1].strip()
+    return response
+
+banner = gr.HTML("""
+    <h1 style="color: #000; font-weight: bold; text-align: center;">
+    OPENASSISTANT
+    </h1>
+    <p style="color: #000; font-weight: bold;">GPT-2 MEDIUM CHATBOT</p>
+    """)
+
+with gr.Blocks(theme=gr.Theme.from_hub('gradio/monochrome')) as demo:
+    banner.render()
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Write your message")
+
+    with gr.Row():
+        clear = gr.Button("Clear chat")
+        submit = gr.Button("Send message")
+
+    def user_input(user_message):
+        response = respond(user_message)
+        return "", [[user_message, response]]
+
+    msg.submit(user_input, [msg], [msg, chatbot], queue=False)
+    clear.click(lambda: None, None, chatbot, queue=False)
+    submit.click(lambda: msg.submit(), None, chatbot, queue=False)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(share=True)