Alexis Ross
commited on
Commit
β’
2d8a250
1
Parent(s):
51d0a37
changes to readme
Browse files
README.md
CHANGED
@@ -7,25 +7,25 @@ widget:
|
|
7 |
- text: "[VERB+passive+past: break | PATIENT+partial: cup] <extra_id_0> <extra_id_1> <extra_id_2> ."
|
8 |
- max_length:
|
9 |
---
|
10 |
-
|
11 |
# Tailor
|
12 |
-
|
13 |
## Model description
|
14 |
-
|
15 |
This is a ported version of [Tailor](https://homes.cs.washington.edu/~wtshuang/static/papers/2021-arxiv-tailor.pdf), the general-purpose counterfactual generator.
|
16 |
For more code release, please refer to [this github page](https://github.com/allenai/tailor).
|
17 |
-
|
18 |
#### How to use
|
19 |
-
|
20 |
```python
|
21 |
from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
|
22 |
-
|
23 |
model_path = "allenai/tailor"
|
24 |
generator = pipeline("text2text-generation",
|
25 |
model=AutoModelForSeq2SeqLM.from_pretrained(model_path),
|
26 |
tokenizer=AutoTokenizer.from_pretrained(model_path),
|
27 |
framework="pt", device=0)
|
28 |
-
|
29 |
prompt_text = "[VERB+active+past: comfort | AGENT+complete: the doctor | PATIENT+partial: athlete | LOCATIVE+partial: in] <extra_id_0> , <extra_id_1> <extra_id_2> <extra_id_3> ."
|
30 |
generator(prompt_text, max_length=200)
|
31 |
```
|
7 |
- text: "[VERB+passive+past: break | PATIENT+partial: cup] <extra_id_0> <extra_id_1> <extra_id_2> ."
|
8 |
- max_length:
|
9 |
---
|
10 |
+
|
11 |
# Tailor
|
12 |
+
|
13 |
## Model description
|
14 |
+
|
15 |
This is a ported version of [Tailor](https://homes.cs.washington.edu/~wtshuang/static/papers/2021-arxiv-tailor.pdf), the general-purpose counterfactual generator.
|
16 |
For more code release, please refer to [this github page](https://github.com/allenai/tailor).
|
17 |
+
|
18 |
#### How to use
|
19 |
+
|
20 |
```python
|
21 |
from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
|
22 |
+
|
23 |
model_path = "allenai/tailor"
|
24 |
generator = pipeline("text2text-generation",
|
25 |
model=AutoModelForSeq2SeqLM.from_pretrained(model_path),
|
26 |
tokenizer=AutoTokenizer.from_pretrained(model_path),
|
27 |
framework="pt", device=0)
|
28 |
+
|
29 |
prompt_text = "[VERB+active+past: comfort | AGENT+complete: the doctor | PATIENT+partial: athlete | LOCATIVE+partial: in] <extra_id_0> , <extra_id_1> <extra_id_2> <extra_id_3> ."
|
30 |
generator(prompt_text, max_length=200)
|
31 |
```
|