llm-latent-language
llm-latent-language copied to clipboard
Some minor weird things I noticed
- The output format of this one seems weird: https://github.com/epfl-dlab/llm-latent-language/blob/1be3cd6eaf14c7408e8f03703d1c1905a6b00c44/Translation.ipynb#L242 E.g. some column are called "de" but contains french words.
- This line should use
lang_latent
and not'en'
: https://github.com/epfl-dlab/llm-latent-language/blob/1be3cd6eaf14c7408e8f03703d1c1905a6b00c44/Translation.ipynb#L316
Right! Can you make a pull request?
The df_en_de_fr
and its column names not matching the actual languages stem from the fact that we started with de and fr and then since the code is the same for other languages just replace the 'de' with the source language and 'fr' with the target language (or the other way around, not sure anymore).