Update README.md
Browse files
README.md
CHANGED
@@ -1,21 +1,48 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
base_model: google/flan-t5-base
|
|
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
metrics:
|
7 |
- rouge
|
8 |
model-index:
|
9 |
-
- name: coedit-
|
10 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
# coedit-
|
|
|
|
|
17 |
|
18 |
-
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.5978
|
21 |
- Rouge1: 60.5931
|
|
|
1 |
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
base_model: google/flan-t5-base
|
4 |
+
datasets:
|
5 |
+
- grammarly/coedit
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
+
- text-generation-inference
|
9 |
metrics:
|
10 |
- rouge
|
11 |
model-index:
|
12 |
+
- name: coedit-small
|
13 |
results: []
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
widget:
|
17 |
+
- text: >-
|
18 |
+
Fix the grammar: When I grow up, I start to understand what he said is
|
19 |
+
quite right.
|
20 |
+
example_title: Fluency
|
21 |
+
- text: >-
|
22 |
+
Make this text coherent: Their flight is weak. They run quickly through
|
23 |
+
the tree canopy.
|
24 |
+
example_title: Coherence
|
25 |
+
- text: >-
|
26 |
+
Rewrite to make this easier to understand: A storm surge is what
|
27 |
+
forecasters consider a hurricane's most treacherous aspect.
|
28 |
+
example_title: Simplification
|
29 |
+
- text: 'Paraphrase this: Do you know where I was born?'
|
30 |
+
example_title: Paraphrase
|
31 |
+
- text: >-
|
32 |
+
Write this more formally: omg i love that song im listening to it right
|
33 |
+
now
|
34 |
+
example_title: Formalize
|
35 |
+
- text: 'Write in a more neutral way: The authors'' exposé on nutrition studies.'
|
36 |
+
example_title: Neutralize
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
should probably proofread and complete it, then remove this comment. -->
|
41 |
|
42 |
+
# coedit-small
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the [CoEdIT dataset](https://huggingface.co/datasets/grammarly/coedit).
|
45 |
|
|
|
46 |
It achieves the following results on the evaluation set:
|
47 |
- Loss: 0.5978
|
48 |
- Rouge1: 60.5931
|