VictorSanh
commited on
Commit
•
bad4725
1
Parent(s):
3449b08
small wordings changes
Browse files
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
|
78 |
|
79 |
|Task category|Datasets|
|
80 |
|-|-|
|
81 |
-
|Natural language inference|ANLI, CB,
|
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|
|