Almost everyone prefers 2048 max tokens because of the superior coherency. It should only be lower due to ram limits, but the menu already shows the optimal ram for 2048. Negatively effected users can turn it down themselves, for everyone else especially on rented machines or colab 2048 is a better default.
Generated using:
```
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("facebook/opt-350m", fast=False)
badwordsids_opt = [[v] for k, v in tokenizer.vocab.items() if any(c in k for c in "<>[]")]
```
OPT supports newlines, but it also needs some of the behavior we use in S mode. NS mode is a more limited version of S mode that still handles the </s> token, but instead of replacing it with a new line we replace it empty and newlines are not converted.
In future if your Fairseq style model has newline support use NS mode, while if it needs artifically inserted newlines use S mode. This also means that people finetuning fairseq models to include newlines might benefit from testing their models on ns mode.
This is to match the behaviour of the original transformers downloader
in order to deal with the rare case of someone downloading a model using
aria2, cancelling before it finishes, and then attempting to resume the
download with the normal transformers downloader.
Trunc prevents slow allocation on windows, force_download=True has proven a more reliable default. Since models are converted to local formats it does not impact local users. And because -c is used the impact of checking if the model is correct is desirable and minimal.
