Update app.py

app.py

@@ -1,63 +1,47 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
 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("betajuned/GPT-2_Kombinasi4")
-
-
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import torch
+
+
+title = "????AI ChatBot"
+description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
+examples = [["How are you?"]]
+
+
+tokenizer = AutoTokenizer.from_pretrained("betajuned/GPT-2_Kombinasi4")
+model = AutoModelForCausalLM.from_pretrained("betajuned/GPT-2_Kombinasi4")
+
+
+def predict(input, history=[]):
+    # tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(
+        input + tokenizer.eos_token, return_tensors="pt"
+    )
+
+    # append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+
+    # generate a response
+    history = model.generate(
+        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
+    ).tolist()
+
+    # convert the tokens to text, and then split the responses into lines
+    response = tokenizer.decode(history[0]).split("<|endoftext|>")
+    # print('decoded_response-->>'+str(response))
+    response = [
+        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
+    ]  # convert to tuples of list
+    # print('response-->>'+str(response))
+    return response, history
+
+
+gr.Interface(
+    fn=predict,
+    title=title,
+    description=description,
+    examples=examples,
+    inputs=["text", "state"],
+    outputs=["chatbot", "state"],
+    theme="finlaymacklon/boxy_violet",
+).launch()