VictorSanh commited on
Commit
bad4725
1 Parent(s): 3449b08

small wordings changes

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -13,7 +13,7 @@ You can use the models to perform inference on tasks by specifying your query in
13
 
14
  # How to use
15
 
16
- We make available the models presented in our [paper](TODO) along with the ablation models. We recommend using the [T0pp_11B](https://huggingface.co/bigscience/T0pp_11B) checkpoint as it leads (on average) to the best performances on a variety of NLP tasks.
17
 
18
  |Model|Number of parameters|
19
  |-|-|
@@ -74,11 +74,11 @@ For reproducibility, we release the data we used for training (and evaluation) i
74
 
75
  # Evaluation data
76
 
77
- We systematically evaluate our models on a suite of held-out tasks:
78
 
79
  |Task category|Datasets|
80
  |-|-|
81
- |Natural language inference|ANLI, CB, HANS, RTE|
82
  |Coreference resolution|WSC, Winogrande|
83
  |Word sense disambiguation|WiC|
84
  |Sentence completion|COPA, HellaSwag, Story Cloze|
 
13
 
14
  # How to use
15
 
16
+ We make available the models presented in our [paper](TODO) along with the ablation models. We recommend using the [T0pp_11B](https://huggingface.co/bigscience/T0pp_11B) (pronounce "T zero plus plus") checkpoint as it leads (on average) to the best performances on a variety of NLP tasks.
17
 
18
  |Model|Number of parameters|
19
  |-|-|
 
74
 
75
  # Evaluation data
76
 
77
+ We evaluate our models on a suite of held-out tasks:
78
 
79
  |Task category|Datasets|
80
  |-|-|
81
+ |Natural language inference|ANLI, CB, RTE|
82
  |Coreference resolution|WSC, Winogrande|
83
  |Word sense disambiguation|WiC|
84
  |Sentence completion|COPA, HellaSwag, Story Cloze|