Commit
•
e91bb19
1
Parent(s):
82820e0
Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,7 @@ This model is based on the T5-base model. We used "transfer learning" to get our
|
|
| 36 |
|
| 37 |
[Kaggle](https://www.kaggle.com/datasets/vladimirvorobevv/chatgpt-paraphrases) link
|
| 38 |
|
| 39 |
-
|
| 40 |
```python
|
| 41 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 42 |
|
|
@@ -76,7 +76,7 @@ def paraphrase(
|
|
| 76 |
return res
|
| 77 |
```
|
| 78 |
|
| 79 |
-
|
| 80 |
|
| 81 |
**Input:**
|
| 82 |
```python
|
|
@@ -107,7 +107,7 @@ paraphrase(text)
|
|
| 107 |
```
|
| 108 |
|
| 109 |
|
| 110 |
-
|
| 111 |
```python
|
| 112 |
epochs = 5
|
| 113 |
batch_size = 64
|
|
@@ -116,9 +116,11 @@ lr = 5e-5
|
|
| 116 |
batches_qty = 196465
|
| 117 |
betas = (0.9, 0.999)
|
| 118 |
eps = 1e-08
|
| 119 |
-
|
| 120 |
-
```
|
| 121 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
@inproceedings{chatgpt_paraphraser,
|
| 123 |
author={Vladimir Vorobev, Maxim Kuznetsov},
|
| 124 |
title={A paraphrasing model based on ChatGPT paraphrases},
|
|
|
|
| 36 |
|
| 37 |
[Kaggle](https://www.kaggle.com/datasets/vladimirvorobevv/chatgpt-paraphrases) link
|
| 38 |
|
| 39 |
+
## Deploying example
|
| 40 |
```python
|
| 41 |
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
|
| 42 |
|
|
|
|
| 76 |
return res
|
| 77 |
```
|
| 78 |
|
| 79 |
+
## Usage examples
|
| 80 |
|
| 81 |
**Input:**
|
| 82 |
```python
|
|
|
|
| 107 |
```
|
| 108 |
|
| 109 |
|
| 110 |
+
## Train parameters
|
| 111 |
```python
|
| 112 |
epochs = 5
|
| 113 |
batch_size = 64
|
|
|
|
| 116 |
batches_qty = 196465
|
| 117 |
betas = (0.9, 0.999)
|
| 118 |
eps = 1e-08
|
|
|
|
|
|
|
| 119 |
```
|
| 120 |
+
|
| 121 |
+
### BibTeX entry and citation info
|
| 122 |
+
|
| 123 |
+
```bibtex
|
| 124 |
@inproceedings{chatgpt_paraphraser,
|
| 125 |
author={Vladimir Vorobev, Maxim Kuznetsov},
|
| 126 |
title={A paraphrasing model based on ChatGPT paraphrases},
|