README.md

---
license: mit
datasets:
- daily_dialog
- multi_woz_v22
language:
- en
---
### Useless ChitChat Language Model

Basic Dialog Model from DialoGPT-small.
Finetuned on Dialog dataset. (Daily Dialog, MultiWoz)  

### How to use

Use it as any torch python Language Model

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("gpt")
model = AutoModelForCausalLM.from_pretrained("jinymusim/dialogmodel")

# Take user Input
user_utterance = input('USER> ')
user_utterance = user_utterance.strip()
tokenized_context = tokenizer.encode(user_utterance + tokenizer.eos_token, return_tensors='pt')

# generated a response, limit max_lenght to resonable size 
out_response = model.generate(tokenized_context, 
                                max_length=100,
                                num_beams=2,
                                no_repeat_ngram_size=2,
                                early_stopping=True,
                                pad_token_id=self.tokenizer.eos_token_id)

# Truncate User Input
decoded_response = self.tokenizer.decode(out_response[0], skip_special_tokens=True)[len(user_utterance):]

print(f'SYSTEM> {decoded_response}')
```