uer
/

t5-small-chinese-cluecorpussmall

Text2Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

uer commited on Mar 19, 2021

Commit

542711e

•

1 Parent(s): 8e8aac5

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -18,8 +18,8 @@ The Text-to-Text Transfer Transformer (T5) leveraged a unified text-to-text form
 |          |           Link           |
 | -------- | :-----------------------: |
-| **Small**  | [**Small**][small] |
-| **Base**  | [**Base**][base] |
 In T5, spans of the input sequence are masked by so-called sentinel token. Each sentinel token represents a unique mask token for the input sequence and should start with <extra_id_0>, <extra_id_1>, … up to <extra_id_199>. However, <extra_id_xxx> is separated into multiple parts in Huggingface's Hosted inference API. Therefore, we replace <extra_id_xxx> with extraxxx in vocabulary and BertTokenizer regards extraxxx as one sentinel token.

 |          |           Link           |
 | -------- | :-----------------------: |
+| **T5-Small**  | [**L=6/H=512 (Small)**][small] |
+| **T5-Base**  | [**L=12/H=768 (Base)**][base] |
 In T5, spans of the input sequence are masked by so-called sentinel token. Each sentinel token represents a unique mask token for the input sequence and should start with <extra_id_0>, <extra_id_1>, … up to <extra_id_199>. However, <extra_id_xxx> is separated into multiple parts in Huggingface's Hosted inference API. Therefore, we replace <extra_id_xxx> with extraxxx in vocabulary and BertTokenizer regards extraxxx as one sentinel token.