Duplicate from Wootang01/chatbot

Co-authored-by: David Woo <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,46 @@
+---
+title: Chatbot
+emoji: 🔥
+colorFrom: blue
+colorTo: yellow
+sdk: streamlit
+app_file: app.py
+pinned: false
+duplicated_from: Wootang01/chatbot
+---
+
+# Configuration
+
+`title`: _string_
+Display title for the Space
+
+`emoji`: _string_
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_
+Can be either `gradio`, `streamlit`, or `static`
+
+`sdk_version` : _string_
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_
+Path to your main application file (which contains either `gradio` or `streamlit` Python code, or `static` html code).
+Path is relative to the root of the repository.
+
+`models`: _List[string]_
+HF model IDs (like "gpt2" or "deepset/roberta-base-squad2") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`datasets`: _List[string]_
+HF dataset IDs (like "common_voice" or "oscar-corpus/OSCAR-2109") used in the Space.
+Will be parsed automatically from your code if not specified here.
+
+`pinned`: _boolean_
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,42 @@
+import streamlit as st
+import torch
+import transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+def load_data():
+  tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
+  model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")
+  return tokenizer, model
+
+tokenizer, model = load_data()
+
+st.title("Chat with a Machine")
+st.write("Write a text message as if writing a text message to a human. The machine will attempt to respond with an appropriate text message.")
+input = st.text_input('Your text message:')
+
+if 'count' not in st.session_state or st.session_state.count == 6:
+  st.session_state.count = 0 
+  st.session_state.chat_history_ids = None
+  st.session_state.old_response = ''
+else:
+  st.session_state.count += 1
+
+# 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([st.session_state.chat_history_ids, new_user_input_ids], dim=-1) if st.session_state.count > 1 else new_user_input_ids
+
+# generate a response 
+st.session_state.chat_history_ids = model.generate(bot_input_ids, max_length=500, pad_token_id=tokenizer.eos_token_id)
+
+# convert the tokens to text, and then split the responses into lines
+response = tokenizer.decode(st.session_state.chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+
+if st.session_state.old_response == response:
+  bot_input_ids = new_user_input_ids
+  st.session_state.chat_history_ids = model.generate(bot_input_ids, max_length=5000, pad_token_id=tokenizer.eos_token_id)
+  response = tokenizer.decode(st.session_state.chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+  
+st.write(f"Machine text message: {response}")
+st.session_state.old_response = response

requirements.txt

@@ -0,0 +1,3 @@
+transformers
+streamlit
+torch