The Blender chatbot model was proposed in Recipes for building an open-domain chatbot Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston on 30 Apr 2020.
The abstract of the paper is the following:
Building open-domain chatbots is a challenging area for machine learning research. While prior work has shown that scaling neural models in the number of parameters and the size of the data they are trained on gives improved results, we show that other ingredients are important for a high-performing chatbot. Good conversation requires a number of skills that an expert conversationalist blends in a seamless way: providing engaging talking points and listening to their partners, and displaying knowledge, empathy and personality appropriately, while maintaining a consistent persona. We show that large scale models can learn these skills when given appropriate training data and choice of generation strategy. We build variants of these recipes with 90M, 2.7B and 9.4B parameter models, and make our models and code publicly available. Human evaluations show our best models are superior to existing approaches in multi-turn dialogue in terms of engagingness and humanness measurements. We then discuss the limitations of this work by analyzing failure cases of our models.
This model was contributed by sshleifer. The authors' code can be found here .
Blenderbot is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than the left.
An example:
>>> from transformers import BlenderbotTokenizer, BlenderbotForConditionalGeneration
>>> mname = "facebook/blenderbot-400M-distill"
>>> model = BlenderbotForConditionalGeneration.from_pretrained(mname)
>>> tokenizer = BlenderbotTokenizer.from_pretrained(mname)
>>> UTTERANCE = "My friends are cool but they eat too many carbs."
>>> inputs = tokenizer([UTTERANCE], return_tensors="pt")
>>> reply_ids = model.generate(**inputs)
>>> print(tokenizer.batch_decode(reply_ids))
["<s> That's unfortunate. Are they trying to lose weight or are they just trying to be healthier?</s>"]- Blenderbot uses a standard seq2seq model transformer based architecture.
- Available checkpoints can be found in the model hub.
- This is the default Blenderbot model class. However, some smaller checkpoints, such as
facebook/blenderbot_small_90M, have a different architecture and consequently should be used with BlenderbotSmall.
[[autodoc]] BlenderbotConfig
[[autodoc]] BlenderbotTokenizer - build_inputs_with_special_tokens
[[autodoc]] BlenderbotTokenizerFast - build_inputs_with_special_tokens
See [~transformers.BartModel] for arguments to forward and generate
[[autodoc]] BlenderbotModel - forward
See [~transformers.BartForConditionalGeneration] for arguments to forward and generate
[[autodoc]] BlenderbotForConditionalGeneration - forward
[[autodoc]] BlenderbotForCausalLM - forward
[[autodoc]] TFBlenderbotModel - call
[[autodoc]] TFBlenderbotForConditionalGeneration - call
[[autodoc]] FlaxBlenderbotModel - call - encode - decode
[[autodoc]] FlaxBlenderbotForConditionalGeneration - call - encode - decode