From 4b7e4eef8e22c345c022a3c9ece22454c7697c25 Mon Sep 17 00:00:00 2001 From: Niels Rogge Date: Thu, 16 Sep 2021 09:43:30 +0000 Subject: [PATCH] Fix model card --- README.md | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/README.md b/README.md index 8cfd55b..cc560fd 100644 --- a/README.md +++ b/README.md @@ -20,7 +20,7 @@ XLNet is a new unsupervised language representation learning method based on a n ## Intended uses & limitations -You can use the raw model for masked language modeling, but it's mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?search=xlm-roberta) to look for fine-tuned versions on a task that interests you. +The model is mostly intended to be fine-tuned on a downstream task. See the [model hub](https://huggingface.co/models?search=xlnet) to look for fine-tuned versions on a task that interests you. Note that this model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering. For tasks such as text generation, you should look at models like GPT2. @@ -62,7 +62,3 @@ last_hidden_states = outputs.last_hidden_state bibsource = {dblp computer science bibliography, https://dblp.org} } ``` - - - -