jpwahle commited on
Commit
b85e126
1 Parent(s): d5068ca

Create model card

Browse files
Files changed (1) hide show
  1. README.md +47 -0
README.md ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: "ISO 639-1 code for your language, or `multilingual`"
3
+ thumbnail: "url to a thumbnail used in social sharing"
4
+ tags:
5
+ - array
6
+ - of
7
+ - tags
8
+ license: "any valid license identifier"
9
+ datasets:
10
+ - array of dataset identifiers
11
+ metrics:
12
+ - array of metric identifiers
13
+ widget:
14
+ - text: "question: which description describes the word \" java \" best in the following context? descriptions: [ \" A drink consisting of an infusion of ground coffee beans \" , \" a platform-independent programming lanugage \" , or \" an island in Indonesia to the south of Borneo \" ] context: I like to drink ' java ' in the morning ."
15
+ ---
16
+
17
+ # T5-large for Word Sense Disambiguation
18
+
19
+ This is the checkpoint for T5-large after being trained on the [SemCor 3.0 dataset](http://lcl.uniroma1.it/wsdeval/).
20
+
21
+ Additional information about this model:
22
+
23
+ * [The t5-large model page](https://huggingface.co/t5-large)
24
+ * [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://arxiv.org/pdf/1910.10683.pdf)
25
+ * [Official implementation by Google](https://github.com/google-research/text-to-text-transfer-transformer)
26
+
27
+ The model can be loaded to perform a few-shot classification like so:
28
+
29
+ ```py
30
+ from transformers import AutoModelForConditionalGeneration, AutoTokenizer
31
+
32
+ AutoModelForConditionalGeneration.from_pretrained("jpelhaw/t5-word-sense-disambiguation")
33
+ AutoTokenizer("jpelhaw/t5-word-sense-disambiguation")
34
+
35
+ input = 'question: which description describes the word " peculiarities " best in the following context? \
36
+ descriptions: [ " an odd or unusual characteristic " , " a distinguishing trait " , or " something unusual -- perhaps worthy of collecting " ] \
37
+ context: The art of change-ringing is peculiar to the English , and , like most English \' peculiarities \' , unintelligible to the rest of the world .'
38
+
39
+
40
+ example = tokenizer.tokenize(input, add_special_tokens=True)
41
+
42
+ answer = model.generate(input_ids=example['input_ids'],
43
+ attention_mask=example['attention_mask'],
44
+ max_length=135)
45
+
46
+ # "a distinguishing trait"
47
+ ```