Update space

app.py

@@ -1,63 +1,38 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 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")
+tokenizer = AutoTokenizer.from_pretrained("Dennterry/okt_bot")
+model = AutoModelForCausalLM.from_pretrained("Dennterry/okt_bot")
 
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+def dialogpt(text):
+    # encode the new user input, add the eos_token and return a tensor in Pytorch
+    for step in range(50000):
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+        new_user_input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors='pt')
 
-    messages.append({"role": "user", "content": message})
+        # append the new user input tokens to the chat history
+        bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
 
-    response = ""
+        # generated a response while limiting the total chat history to 1000 tokens,
+        chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
 
-    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
+        # pretty print last ouput tokens from bot
+        return tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
 
-        response += token
-        yield response
+inputs = gr.inputs.Textbox(lines=1, label="Input Text")
+outputs =  gr.outputs.Textbox(label="DialoGPT")
 
-"""
-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()
+title = "DialoGPT"
+description = "demo for Microsoft DialoGPT with Hugging Face transformers. To use it, simply input text or click one of the examples text to load them. Read more at the links below. *This is not a Microsoft product and is developed for Gradio*"
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1911.00536'>DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation</a> | <a href='https://github.com/microsoft/DialoGPT'>Github Repo</a> | <a href='https://huggingface.co/microsoft/DialoGPT-large'>Hugging Face DialoGPT-large</a></p>"
+examples = [
+            ["Hi, how are you?"],
+            ["How far away is the moon?"],
+]
+
+gr.Interface(dialogpt, inputs, outputs, title=title, description=description, article=article, examples=examples).launch(debug=True)