Edit model card

This model is a fine-tuned version of facebook/nllb-200-3.3B on the EasyProject dataset.

Framework versions

Code

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained(
        "facebook/nllb-200-distilled-600M",  src_lang="eng_Latn")
    
print("Loading model")
model = AutoModelForSeq2SeqLM.from_pretrained("ychenNLP/nllb-200-3.3b-easyproject")
model.cuda()

input_chunks = ["A translator always risks inadvertently introducing source-language words, grammar, or syntax into the target-language rendering."]
print("Start translation...")
output_result = []

batch_size = 1
for idx in tqdm(range(0, len(input_chunks), batch_size)):
    start_idx = idx
    end_idx = idx + batch_size
    inputs = tokenizer(input_chunks[start_idx: end_idx], padding=True, truncation=True, max_length=128, return_tensors="pt").to('cuda')

    with torch.no_grad():
        translated_tokens = model.generate(**inputs, forced_bos_token_id=tokenizer.lang_code_to_id["zho_Hans"], 
                        max_length=128, num_beams=5, num_return_sequences=1, early_stopping=True)

    output = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True)
    output_result.extend(output)
print(output_result)

Citation

@inproceedings{chen2023easyproject,
  title={Frustratingly Easy Label Projection for Cross-lingual Transfer},
  author={Chen, Yang and Jiang, Chao and Ritter, Alan and Xu, Wei},
  booktitle={Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Findings)},
  year={2023}
}
Downloads last month
247
Inference Examples
Inference API (serverless) has been turned off for this model.

Space using ychenNLP/nllb-200-3.3B-easyproject 1