TF XLNet

92b3cb78 · Lysandre · Lysandre Debut · cd656fb2 · 92b3cb78 · 92b3cb78
Commit 92b3cb78 authored Jan 17, 2020 by Lysandre Committed by Lysandre Debut Jan 23, 2020
Expand all Show whitespace changes
Inline Side-by-side

Showing with 190 additions and 190 deletions

src/transformers/modeling_tf_xlnet.py src/transformers/modeling_tf_xlnet.py +188 -189

src/transformers/modeling_xlnet.py src/transformers/modeling_xlnet.py +2 -1

No files found.
--- a/src/transformers/modeling_tf_xlnet.py
+++ b/src/transformers/modeling_tf_xlnet.py
--- a/src/transformers/modeling_xlnet.py
+++ b/src/transformers/modeling_xlnet.py
@@ -1092,7 +1092,8 @@ class XLNetForSequenceClassification(XLNetPreTrainedModel):
            If ``config.num_labels == 1`` a regression loss is computed (Mean-Square loss),
            If ``config.num_labels > 1`` a classification loss is computed (Cross-Entropy).

-    Outputs: `Tuple` comprising various elements depending on the configuration (config) and inputs:
+    Return:
+        `tuple(torch.FloatTensor)` comprising various elements depending on the configuration (config) and inputs:
        loss (:obj:`torch.FloatTensor` of shape :obj:`(1,)`, `optional`, returned when :obj:`labels` is provided):
            Classification (or regression if config.num_labels==1) loss.
        logits (:obj:`torch.FloatTensor` of shape :obj:(batch_size, config.num_labels)`):