Total runs:
275.7K
Run Growth:
-44.1K
Growth Rate:
-15.90%
Sponsored by
PoYo.AI
mrm8488 / t5-small-finetuned-quora-for-paraphrasing
Model's Last Updated: December 12 2020
text-generation
Introduction of t5-small-finetuned-quora-for-paraphrasing
Model Details of t5-small-finetuned-quora-for-paraphrasing
T5-base fine-tuned on Quora question pair dataset for Question Paraphrasing ❓↔️❓
Google's T5 fine-tuned on Quodra question pair dataset for Question Paraphrasing task.
Details of T5
The T5 model was presented in Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer by Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, Peter J. Liu in Here the abstract:
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts every language problem into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled datasets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new “Colossal Clean Crawled Corpus”, we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our dataset, pre-trained models, and code.
Details of the downstream task (Question Paraphrasing) - Dataset 📚❓↔️❓
Dataset ID:
quora
from
Huggingface/NLP
| Dataset | Split | # samples |
|---|---|---|
| quora | train | 404290 |
| quora after filter repeated questions | train | 149263 |
Check out more about this dataset and others in NLP Viewer
Model fine-tuning 🏋️
The training script is a slightly modified version of this one
Model in Action 🚀
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-small-finetuned-quora-for-paraphrasing")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-small-finetuned-quora-for-paraphrasing")
def paraphrase(text, max_length=128):
input_ids = tokenizer.encode(text, return_tensors="pt", add_special_tokens=True)
generated_ids = model.generate(input_ids=input_ids, num_return_sequences=5, num_beams=5, max_length=max_length, no_repeat_ngram_size=2, repetition_penalty=3.5, length_penalty=1.0, early_stopping=True)
preds = [tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in generated_ids]
return preds
preds = paraphrase("paraphrase: What is the best framework for dealing with a huge text dataset?")
for pred in preds:
print(pred)
# Output:
'''
What is the best framework for dealing with a huge text dataset?
What is the best framework for dealing with a large text dataset?
What is the best framework to deal with a huge text dataset?
What are the best frameworks for dealing with a huge text dataset?
What is the best framework for dealing with huge text datasets?
'''
Created by Manuel Romero/@mrm8488 | LinkedIn
Made with ♥ in Spain
Runs of mrm8488 t5-small-finetuned-quora-for-paraphrasing on huggingface.co
214
Total runs
0
24-hour runs
5
3-day runs
16
7-day runs
77
30-day runs
More Information About t5-small-finetuned-quora-for-paraphrasing huggingface.co Model
Url of t5-small-finetuned-quora-for-paraphrasing
t5-small-finetuned-quora-for-paraphrasing huggingface.co Url
Provider of t5-small-finetuned-quora-for-paraphrasing huggingface.co
Other API from mrm8488
Updated:January 21 2024
Total runs:
33.6K
Run Growth:
5.5K
Growth Rate:
16.39%
Total runs:
19.3K
Run Growth:
3.5K
Growth Rate:
18.26%
Total runs:
13.2K
Run Growth:
396
Growth Rate:
3.00%
Total runs:
9.5K
Run Growth:
4.9K
Growth Rate:
50.91%
Total runs:
8.7K
Run Growth:
5.7K
Growth Rate:
65.22%
Total runs:
8.7K
Run Growth:
3.3K
Growth Rate:
37.44%
Total runs:
8.4K
Run Growth:
-1.2K
Growth Rate:
-13.30%
Total runs:
5.9K
Run Growth:
226
Growth Rate:
3.83%
Total runs:
4.6K
Run Growth:
4.1K
Growth Rate:
88.85%
Total runs:
4.4K
Run Growth:
109
Growth Rate:
2.49%
Total runs:
3.0K
Run Growth:
-8
Growth Rate:
-0.27%
Total runs:
1.6K
Run Growth:
1.0K
Growth Rate:
63.80%
Total runs:
1.5K
Run Growth:
145
Growth Rate:
9.91%
Total runs:
958
Run Growth:
89
Growth Rate:
9.29%
Total runs:
917
Run Growth:
-1.4K
Growth Rate:
-153.11%
Total runs:
910
Run Growth:
326
Growth Rate:
35.82%
Total runs:
835
Run Growth:
-958
Growth Rate:
-114.73%
Total runs:
808
Run Growth:
11
Growth Rate:
1.39%
Total runs:
796
Run Growth:
-274
Growth Rate:
-34.42%
Total runs:
733
Run Growth:
-128
Growth Rate:
-17.46%
Total runs:
683
Run Growth:
-1.7K
Growth Rate:
-253.00%
Total runs:
682
Run Growth:
335
Growth Rate:
49.12%
Total runs:
654
Run Growth:
212
Growth Rate:
32.92%
Total runs:
490
Run Growth:
295
Growth Rate:
58.42%
Total runs:
464
Run Growth:
366
Growth Rate:
78.88%
Total runs:
454
Run Growth:
-3.2K
Growth Rate:
-696.04%
Total runs:
392
Run Growth:
-111
Growth Rate:
-29.13%
Total runs:
366
Run Growth:
57
Growth Rate:
15.57%
Total runs:
353
Run Growth:
23
Growth Rate:
6.74%
Total runs:
326
Run Growth:
88
Growth Rate:
26.99%
Total runs:
308
Run Growth:
229
Growth Rate:
75.33%
Total runs:
300
Run Growth:
-48
Growth Rate:
-16.00%
Total runs:
269
Run Growth:
24
Growth Rate:
8.92%
Total runs:
264
Run Growth:
244
Growth Rate:
96.06%
Total runs:
260
Run Growth:
255
Growth Rate:
98.08%
Total runs:
250
Run Growth:
-122
Growth Rate:
-48.80%
Total runs:
242
Run Growth:
-17
Growth Rate:
-7.02%
Total runs:
237
Run Growth:
80
Growth Rate:
33.76%
Total runs:
227
Run Growth:
-197
Growth Rate:
-86.78%
Total runs:
213
Run Growth:
-37
Growth Rate:
-17.37%
Total runs:
195
Run Growth:
-190
Growth Rate:
-96.94%
Total runs:
187
Run Growth:
15
Growth Rate:
8.02%
Total runs:
154
Run Growth:
120
Growth Rate:
77.92%
Total runs:
149
Run Growth:
125
Growth Rate:
82.24%
Total runs:
147
Run Growth:
40
Growth Rate:
27.97%
Total runs:
143
Run Growth:
47
Growth Rate:
32.87%
Total runs:
134
Run Growth:
107
Growth Rate:
79.85%
Total runs:
133
Run Growth:
-33
Growth Rate:
-24.81%
Total runs:
122
Run Growth:
50
Growth Rate:
40.98%
Total runs:
121
Run Growth:
68
Growth Rate:
56.20%
Total runs:
119
Run Growth:
98
Growth Rate:
80.99%
Total runs:
116
Run Growth:
38
Growth Rate:
32.76%
Total runs:
115
Run Growth:
47
Growth Rate:
40.87%
Total runs:
114
Run Growth:
-91
Growth Rate:
-79.82%
Total runs:
114
Run Growth:
34
Growth Rate:
29.82%
Total runs:
112
Run Growth:
54
Growth Rate:
47.79%
Total runs:
107
Run Growth:
74
Growth Rate:
69.16%
Total runs:
105
Run Growth:
19
Growth Rate:
17.59%
Total runs:
105
Run Growth:
95
Growth Rate:
90.48%
Total runs:
101
Run Growth:
60
Growth Rate:
59.41%
Total runs:
101
Run Growth:
26
Growth Rate:
25.74%
Total runs:
99
Run Growth:
7
Growth Rate:
7.07%
Total runs:
92
Run Growth:
68
Growth Rate:
73.91%
Total runs:
89
Run Growth:
72
Growth Rate:
83.72%
Total runs:
88
Run Growth:
12
Growth Rate:
13.95%
Total runs:
88
Run Growth:
-120
Growth Rate:
-136.36%
Total runs:
88
Run Growth:
-11
Growth Rate:
-12.50%
Total runs:
83
Run Growth:
-29
Growth Rate:
-31.87%
Total runs:
82
Run Growth:
-40
Growth Rate:
-48.78%
Total runs:
82
Run Growth:
57
Growth Rate:
69.51%
Total runs:
81
Run Growth:
73
Growth Rate:
90.12%
Total runs:
77
Run Growth:
-13
Growth Rate:
-16.88%
Total runs:
76
Run Growth:
48
Growth Rate:
63.16%
Total runs:
76
Run Growth:
47
Growth Rate:
61.84%
Total runs:
73
Run Growth:
2
Growth Rate:
2.74%
Total runs:
73
Run Growth:
42
Growth Rate:
61.76%
Total runs:
73
Run Growth:
31
Growth Rate:
42.47%
Total runs:
69
Run Growth:
-46
Growth Rate:
-66.67%
Total runs:
68
Run Growth:
53
Growth Rate:
77.94%
Total runs:
61
Run Growth:
47
Growth Rate:
75.81%
Total runs:
61
Run Growth:
24
Growth Rate:
39.34%
Total runs:
60
Run Growth:
23
Growth Rate:
37.70%
Total runs:
57
Run Growth:
45
Growth Rate:
77.59%
Total runs:
56
Run Growth:
-80
Growth Rate:
-153.85%
Total runs:
55
Run Growth:
33
Growth Rate:
60.00%
Total runs:
55
Run Growth:
47
Growth Rate:
85.45%
Total runs:
55
Run Growth:
4
Growth Rate:
7.27%
Total runs:
54
Run Growth:
12
Growth Rate:
22.22%
Total runs:
54
Run Growth:
37
Growth Rate:
68.52%
Total runs:
52
Run Growth:
30
Growth Rate:
57.69%
Total runs:
49
Run Growth:
30
Growth Rate:
57.69%