blenderbot-400M-esconv

blenderbot-400M-distill fine-tuned on the ESConv dataset. Usage example:

import torch
from transformers import AutoTokenizer
from transformers.models.blenderbot import BlenderbotTokenizer, BlenderbotForConditionalGeneration

def _norm(x):
    return ' '.join(x.strip().split())

tokenizer = BlenderbotTokenizer.from_pretrained('thu-coai/blenderbot-400M-esconv')
model = BlenderbotForConditionalGeneration.from_pretrained('thu-coai/blenderbot-400M-esconv')
model.eval()

utterances = [
    "I am having a lot of anxiety about quitting my current job. It is too stressful but pays well",
    "What makes your job stressful for you?",
    "I have to deal with many people in hard financial situations and it is upsetting",
    "Do you help your clients to make it to a better financial situation?",
    "I do, but often they are not going to get back to what they want. Many people are going to lose their home when safeguards are lifted",
]
input_sequence = '  '.join([' ' + e for e in utterances]) + tokenizer.eos_token # add space prefix and separate utterances with two spaces
input_ids = tokenizer.convert_tokens_to_ids(tokenizer.tokenize(input_sequence))[-128:]
input_ids = torch.LongTensor([input_ids])

model_output = model.generate(input_ids, num_beams=1, do_sample=True, top_p=0.9, num_return_sequences=5, return_dict=False)
generation = tokenizer.batch_decode(model_output, skip_special_tokens=True)
generation = [_norm(e) for e in generation]
print(generation)

utterances.append(generation[0]) # for future loop

Please kindly cite the original paper if you use this model:

@inproceedings{liu-etal-2021-towards,
  title={Towards Emotional Support Dialog Systems},
  author={Liu, Siyang  and 
    Zheng, Chujie  and 
    Demasi, Orianna  and 
    Sabour, Sahand  and 
    Li, Yu  and 
    Yu, Zhou  and 
    Jiang, Yong  and 
    Huang, Minlie},
  booktitle={Proceedings of the 59th annual meeting of the Association for Computational Linguistics},
  year={2021}
}