Transformers
PyTorch
TensorFlow
JAX
English
blenderbot
text2text-generation
convAI
conversational
facebook
Instructions to use facebook/blenderbot-400M-distill with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/blenderbot-400M-distill with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/blenderbot-400M-distill", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Outdated?
#23
by mangoszteen - opened
It seems like the pipeline for "conversational" has been removed, but the suggested code still uses a conversational type of input:
Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text2text-generation", model="facebook/blenderbot-400M-distill")
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages)
This code leads to an error.