|
--- |
|
thumbnail: https://huggingface.co/front/thumbnails/dialogpt.png |
|
tags: |
|
- conversational |
|
license: mit |
|
--- |
|
# DialoGPT Trained on WhatsApp chats |
|
This is an instance of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium) trained on WhatsApp chats or you can train this model on [a Kaggle game script dataset](https://www.kaggle.com/ruolinzheng/twewy-game-script). |
|
feel free to ask me questions on discord server [discord server](https://discord.gg/Gqhje8Z7DX) |
|
Chat with the model: |
|
```python |
|
from transformers import AutoTokenizer, AutoModelWithLMHead |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("harrydonni/DialoGPT-small-Michael-Scott") |
|
model = AutoModelWithLMHead.from_pretrained("harrydonni/DialoGPT-small-Michael-Scott") |
|
# Let's chat for 4 lines |
|
for step in range(4): |
|
# encode the new user input, add the eos_token and return a tensor in Pytorch |
|
new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt') |
|
# print(new_user_input_ids) |
|
# 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 |
|
# generated a response while limiting the total chat history to 1000 tokens, |
|
chat_history_ids = model.generate( |
|
bot_input_ids, max_length=200, |
|
pad_token_id=tokenizer.eos_token_id, |
|
no_repeat_ngram_size=3, |
|
do_sample=True, |
|
top_k=100, |
|
top_p=0.7, |
|
temperature=0.8 |
|
) |
|
|
|
# pretty print last ouput tokens from bot |
|
print("Michael: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True))) |
|
``` |
|
this is done by shreesha thank you...... |
