huggingface--transformers/docs/source/en/model_doc/nllb.md

This model was published in HF papers on 2022-07-11 and contributed to Hugging Face Transformers on 2022-07-18.

NLLB

Overview

NLLB: No Language Left Behind is a multilingual translation model. It's trained on data using data mining techniques tailored for low-resource languages and supports over 200 languages. NLLB features a conditional compute architecture using a Sparsely Gated Mixture of Experts.

You can find all the original NLLB checkpoints under the AI at Meta organization.

Tip

This model was contributed by Lysandre. Click on the NLLB models in the right sidebar for more examples of how to apply NLLB to different translation tasks.

The example below demonstrates how to translate text with [Pipeline] or the [AutoModel] class.

from transformers import pipeline


pipeline = pipeline(task="translation", model="facebook/nllb-200-distilled-600M", src_lang="eng_Latn", tgt_lang="fra_Latn", device=0)
pipeline("UN Chief says there is no military solution in Syria")

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M", attn_implementation="sdpa", device_map="auto")

article = "UN Chief says there is no military solution in Syria"
inputs = tokenizer(article, return_tensors="pt").to(model.device)

translated_tokens = model.generate(
    **inputs, forced_bos_token_id=tokenizer.convert_tokens_to_ids("fra_Latn"), max_length=30
)
print(tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0])

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses bitsandbytes to quantize the weights to 8-bits.

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, BitsAndBytesConfig


bnb_config = BitsAndBytesConfig(load_in_8bit=True)
model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-1.3B", quantization_config=bnb_config, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-1.3B")

article = "UN Chief says there is no military solution in Syria"
inputs = tokenizer(article, return_tensors="pt").to(model.device)
translated_tokens = model.generate(
    **inputs, forced_bos_token_id=tokenizer.convert_tokens_to_ids("fra_Latn"), max_length=30,
)
print(tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0])

Use the AttentionMaskVisualizer to better understand what tokens the model can and cannot attend to.

from transformers.utils.attention_visualizer import AttentionMaskVisualizer


visualizer = AttentionMaskVisualizer("facebook/nllb-200-distilled-600M")
visualizer("UN Chief says there is no military solution in Syria")

Notes

• The tokenizer was updated in April 2023 to prefix the source sequence with the source language rather than the target language. This prioritizes zero-shot performance at a minor cost to supervised performance.

  from transformers import NllbTokenizer
  
  tokenizer = NllbTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
  tokenizer("How was your day?").input_ids
  [256047, 13374, 1398, 4260, 4039, 248130, 2]
  

  To revert to the legacy behavior, use the code example below.

  from transformers import NllbTokenizer
  
  tokenizer = NllbTokenizer.from_pretrained("facebook/nllb-200-distilled-600M", legacy_behaviour=True)
  

• For non-English languages, specify the language's BCP-47 code with the src_lang keyword as shown below.

• See example below for a translation from Romanian to German.

  from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
  
  tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
  model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M", device_map="auto")
  
  article = "UN Chief says there is no military solution in Syria"
  inputs = tokenizer(article, return_tensors="pt").to(model.device)
  
  translated_tokens = model.generate(
      **inputs, forced_bos_token_id=tokenizer.convert_tokens_to_ids("fra_Latn"), max_length=30
  )
  tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)[0]
  Le chef de l'ONU dit qu'il n'y a pas de solution militaire en Syrie
  

NllbTokenizer

autodoc NllbTokenizer

NllbTokenizerFast

autodoc NllbTokenizerFast