oscar-corpus/oscar
Updated • 698 • 207
How to use pere/nb-nn-dev2 with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "translation" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline
pipe = pipeline("translation", model="pere/nb-nn-dev2") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pere/nb-nn-dev2", dtype="auto")# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pere/nb-nn-dev2", dtype="auto")This is the development version of the Bokmål-Nynorsk translator. If you want something that is stable, Please do run this version instead.
Here is an example of how to use the model from Python
# Import libraries
from transformers import T5ForConditionalGeneration, AutoTokenizer
model = T5ForConditionalGeneration.from_pretrained('pere/nb-nn-dev',from_flax=True)
tokenizer = AutoTokenizer.from_pretrained('pere/nb-nn-dev')
#Encode the text
text = "Hun vil ikke gi bort sine personlige data."
inputs = tokenizer.encode(text, return_tensors="pt")
outputs = model.generate(inputs, max_length=255, num_beams=4, early_stopping=True)
#Decode and print the result
print(tokenizer.decode(outputs[0]))
Or if you like to use the pipeline instead
# Set up the pipeline
from transformers import pipeline
translator = pipeline("translation", model='pere/nb-nn-dev')
# Do the translation
text = "Hun vil ikke gi bort sine personlige data."
print(translator(text, max_length=255))
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="pere/nb-nn-dev2")