# Transformers installation
! pip install transformers datasets
# To install from source instead of the last release, comment the command above and uncomment the following one.
# ! pip install git+https://github.com/huggingface/transformers.git

import torch
from transformers import XLMTokenizer, XLMWithLMHeadModel

tokenizer = XLMTokenizer.from_pretrained("xlm-clm-enfr-1024")
model = XLMWithLMHeadModel.from_pretrained("xlm-clm-enfr-1024")

print(tokenizer.lang2id)

input_ids = torch.tensor([tokenizer.encode("Wikipedia was used to")])  # batch size of 1

language_id = tokenizer.lang2id["en"]  # 0
langs = torch.tensor([language_id] * input_ids.shape[1])  # torch.tensor([0, 0, 0, ..., 0])

# We reshape it to be of size (batch_size, sequence_length)
langs = langs.view(1, -1)  # is now of shape [1, sequence_length] (we have a batch size of 1)

outputs = model(input_ids, langs=langs)

from transformers import M2M100ForConditionalGeneration, M2M100Tokenizer

en_text = "Do not meddle in the affairs of wizards, for they are subtle and quick to anger."
chinese_text = "不要插手巫師的事務, 因為他們是微妙的, 很快就會發怒."

tokenizer = M2M100Tokenizer.from_pretrained("facebook/m2m100_418M", src_lang="zh")
model = M2M100ForConditionalGeneration.from_pretrained("facebook/m2m100_418M")

encoded_zh = tokenizer(chinese_text, return_tensors="pt")

generated_tokens = model.generate(**encoded_zh, forced_bos_token_id=tokenizer.get_lang_id("en"))
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

en_text = "Do not meddle in the affairs of wizards, for they are subtle and quick to anger."
fi_text = "Älä sekaannu velhojen asioihin, sillä ne ovat hienovaraisia ja nopeasti vihaisia."

tokenizer = AutoTokenizer.from_pretrained("facebook/mbart-large-50-many-to-many-mmt", src_lang="fi_FI")
model = AutoModelForSeq2SeqLM.from_pretrained("facebook/mbart-large-50-many-to-many-mmt")

encoded_en = tokenizer(en_text, return_tensors="pt")

generated_tokens = model.generate(**encoded_en, forced_bos_token_id=tokenizer.lang_code_to_id("en_XX"))
tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)