from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_path = "neverLife/nllb-200-distilled-600M-ja-zh"
model = AutoModelForSeq2SeqLM.from_pretrained(model_path)
ja = "ぜんぜん田舎に来た気がしないんだが……。"
tokenizer = AutoTokenizer.from_pretrained(model_path, src_lang="jpn_Jpan", tgt_lang="zho_Hans")

input_ids = tokenizer.encode(ja, max_length=128, padding=True, return_tensors='pt')
outputs = model.generate(input_ids, num_beams=4, max_new_tokens=128)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

框架版本

Transformers 4.28.1
Pytorch 2.0.0+cu117
Datasets 2.11.0
Tokenizers 0.13.3