From 40040727ab9b58d703797dbb8548e1eee3be1cbe Mon Sep 17 00:00:00 2001 From: Patrick von Platen Date: Wed, 2 Mar 2022 10:24:32 +0100 Subject: [PATCH] [Bart] Fix implementation note doc (#15879) --- docs/source/model_doc/bart.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/model_doc/bart.mdx b/docs/source/model_doc/bart.mdx index 18d0e1e10f..38d6b6ea95 100644 --- a/docs/source/model_doc/bart.mdx +++ b/docs/source/model_doc/bart.mdx @@ -51,7 +51,7 @@ This model was contributed by [sshleifer](https://huggingface.co/sshleifer). The - The forward pass of [`BartModel`] will create the `decoder_input_ids` if they are not passed. This is different than some other modeling APIs. A typical use case of this feature is mask filling. - Model predictions are intended to be identical to the original implementation when - `force_bos_token_to_be_generated=True`. This only works, however, if the string you pass to + `forced_bos_token_id=0`. This only works, however, if the string you pass to [`fairseq.encode`] starts with a space. - [`~generation_utils.GenerationMixin.generate`] should be used for conditional generation tasks like summarization, see the example in that docstrings.