Total runs:
265.7K
Run Growth:
-83.6K
Growth Rate:
-31.28%
Sponsored by
AdsCreator.com
mrm8488 / t5-base-finetuned-question-generation-ap
Model's Last Updated: May 31 2023
text-generation
Introduction of t5-base-finetuned-question-generation-ap
Model Details of t5-base-finetuned-question-generation-ap
T5-base fine-tuned on SQuAD for Question Generation
Google's T5 fine-tuned on SQuAD v1.1 for Question Generation by just prepending the answer to the context .
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 (Q&A) - Dataset 📚 🧐 ❓
Dataset ID:
squad
from
Huggingface/NLP
| Dataset | Split | # samples |
|---|---|---|
| squad | train | 87599 |
| squad | valid | 10570 |
How to load it from nlp
train_dataset = nlp.load_dataset('squad', split=nlp.Split.TRAIN)
valid_dataset = nlp.load_dataset('squad', split=nlp.Split.VALIDATION)
Check out more about this dataset and others in NLP Viewer
Model fine-tuning 🏋️
The training script is a slightly modified version of this awesome one by Suraj Patil
He also made a great research on Question Generation
Model in Action 🚀
# Tip: By now, install transformers from source
from transformers import AutoModelWithLMHead, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
model = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
def get_question(answer, context, max_length=64):
input_text = "answer: %s context: %s </s>" % (answer, context)
features = tokenizer([input_text], return_tensors='pt')
output = model.generate(input_ids=features['input_ids'],
attention_mask=features['attention_mask'],
max_length=max_length)
return tokenizer.decode(output[0])
context = "Manuel has created RuPERTa-base with the support of HF-Transformers and Google"
answer = "Manuel"
get_question(answer, context)
# output: question: Who created the RuPERTa-base?
Citation
If you want to cite this model you can use this:
@misc{mromero2021t5-base-finetuned-question-generation-ap,
title={T5 (base) fine-tuned on SQUAD for QG via AP},
author={Romero, Manuel},
publisher={Hugging Face},
journal={Hugging Face Hub},
howpublished={\url{https://huggingface.co/mrm8488/t5-base-finetuned-question-generation-ap}},
year={2021}
}
Created by Manuel Romero/@mrm8488 | LinkedIn
Made with ♥ in Spain
Runs of mrm8488 t5-base-finetuned-question-generation-ap on huggingface.co
805
Total runs
0
24-hour runs
44
3-day runs
19
7-day runs
-14
30-day runs
More Information About t5-base-finetuned-question-generation-ap huggingface.co Model
Url of t5-base-finetuned-question-generation-ap
t5-base-finetuned-question-generation-ap huggingface.co Url
Provider of t5-base-finetuned-question-generation-ap huggingface.co
Other API from mrm8488
Updated:January 21 2024
Total runs:
65.7K
Run Growth:
49.0K
Growth Rate:
74.57%
Total runs:
33.2K
Run Growth:
353
Growth Rate:
1.08%
Total runs:
13.0K
Run Growth:
-577
Growth Rate:
-4.50%
Total runs:
9.5K
Run Growth:
4.9K
Growth Rate:
50.91%
Total runs:
8.7K
Run Growth:
356
Growth Rate:
4.12%
Total runs:
8.7K
Run Growth:
5.7K
Growth Rate:
65.22%
Total runs:
7.6K
Run Growth:
-4.7K
Growth Rate:
-62.21%
Total runs:
5.9K
Run Growth:
-55
Growth Rate:
-0.94%
Total runs:
4.4K
Run Growth:
1.6K
Growth Rate:
35.76%
Total runs:
3.7K
Run Growth:
-870
Growth Rate:
-22.77%
Total runs:
2.4K
Run Growth:
-1.3K
Growth Rate:
-53.98%
Total runs:
1.5K
Run Growth:
142
Growth Rate:
9.65%
Total runs:
1.4K
Run Growth:
662
Growth Rate:
45.06%
Total runs:
1.1K
Run Growth:
673
Growth Rate:
60.79%
Total runs:
987
Run Growth:
59
Growth Rate:
6.10%
Total runs:
973
Run Growth:
-1.3K
Growth Rate:
-133.57%
Total runs:
779
Run Growth:
59
Growth Rate:
7.44%
Total runs:
682
Run Growth:
335
Growth Rate:
49.12%
Total runs:
680
Run Growth:
-309
Growth Rate:
-47.47%
Total runs:
647
Run Growth:
-219
Growth Rate:
-31.06%
Total runs:
634
Run Growth:
-1.3K
Growth Rate:
-213.56%
Total runs:
617
Run Growth:
75
Growth Rate:
12.16%
Total runs:
475
Run Growth:
-907
Growth Rate:
-187.78%
Total runs:
464
Run Growth:
366
Growth Rate:
78.88%
Total runs:
462
Run Growth:
145
Growth Rate:
31.87%
Total runs:
374
Run Growth:
358
Growth Rate:
95.21%
Total runs:
366
Run Growth:
57
Growth Rate:
15.57%
Total runs:
363
Run Growth:
-189
Growth Rate:
-54.94%
Total runs:
336
Run Growth:
-50
Growth Rate:
-15.24%
Total runs:
326
Run Growth:
88
Growth Rate:
26.99%
Total runs:
324
Run Growth:
197
Growth Rate:
61.76%
Total runs:
300
Run Growth:
-48
Growth Rate:
-16.00%
Total runs:
269
Run Growth:
24
Growth Rate:
8.92%
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:
227
Run Growth:
-197
Growth Rate:
-86.78%
Total runs:
202
Run Growth:
39
Growth Rate:
19.80%
Total runs:
190
Run Growth:
154
Growth Rate:
83.24%
Total runs:
175
Run Growth:
140
Growth Rate:
80.92%
Total runs:
168
Run Growth:
93
Growth Rate:
57.41%
Total runs:
165
Run Growth:
90
Growth Rate:
43.06%
Total runs:
159
Run Growth:
-105
Growth Rate:
-70.47%
Total runs:
154
Run Growth:
120
Growth Rate:
77.92%
Total runs:
150
Run Growth:
-314
Growth Rate:
-205.23%
Total runs:
131
Run Growth:
62
Growth Rate:
46.97%
Total runs:
128
Run Growth:
-39
Growth Rate:
-36.79%
Total runs:
127
Run Growth:
55
Growth Rate:
44.00%
Total runs:
125
Run Growth:
42
Growth Rate:
33.60%
Total runs:
122
Run Growth:
-54
Growth Rate:
-44.26%
Total runs:
120
Run Growth:
-225
Growth Rate:
-181.45%
Total runs:
118
Run Growth:
10
Growth Rate:
9.80%
Total runs:
116
Run Growth:
38
Growth Rate:
32.76%
Total runs:
115
Run Growth:
85
Growth Rate:
73.91%
Total runs:
114
Run Growth:
52
Growth Rate:
45.61%
Total runs:
113
Run Growth:
19
Growth Rate:
16.96%
Total runs:
112
Run Growth:
108
Growth Rate:
89.26%
Total runs:
111
Run Growth:
26
Growth Rate:
24.30%
Total runs:
111
Run Growth:
29
Growth Rate:
26.61%
Total runs:
110
Run Growth:
56
Growth Rate:
50.45%
Total runs:
107
Run Growth:
74
Growth Rate:
69.81%
Total runs:
105
Run Growth:
64
Growth Rate:
62.14%
Total runs:
105
Run Growth:
70
Growth Rate:
66.67%
Total runs:
104
Run Growth:
63
Growth Rate:
60.58%
Total runs:
100
Run Growth:
-8
Growth Rate:
-9.52%
Total runs:
99
Run Growth:
-107
Growth Rate:
-108.08%
Total runs:
94
Run Growth:
-18
Growth Rate:
-19.15%
Total runs:
92
Run Growth:
68
Growth Rate:
73.91%
Total runs:
87
Run Growth:
-71
Growth Rate:
-81.61%
Total runs:
85
Run Growth:
-76
Growth Rate:
-89.41%
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:
79
Run Growth:
51
Growth Rate:
64.56%
Total runs:
78
Run Growth:
-23
Growth Rate:
-36.51%
Total runs:
76
Run Growth:
47
Growth Rate:
61.84%
Total runs:
73
Run Growth:
31
Growth Rate:
42.47%
Total runs:
67
Run Growth:
22
Growth Rate:
34.92%
Total runs:
66
Run Growth:
48
Growth Rate:
77.42%
Total runs:
65
Run Growth:
24
Growth Rate:
36.92%
Total runs:
63
Run Growth:
31
Growth Rate:
50.82%
Total runs:
60
Run Growth:
30
Growth Rate:
50.85%
Total runs:
60
Run Growth:
0
Growth Rate:
0.00%
Total runs:
58
Run Growth:
7
Growth Rate:
12.50%
Total runs:
58
Run Growth:
-104
Growth Rate:
-179.31%
Total runs:
57
Run Growth:
-57
Growth Rate:
-98.28%
Total runs:
57
Run Growth:
-27
Growth Rate:
-47.37%
Total runs:
56
Run Growth:
41
Growth Rate:
73.21%
Total runs:
56
Run Growth:
0
Growth Rate:
0.00%
Total runs:
56
Run Growth:
29
Growth Rate:
51.79%
Total runs:
55
Run Growth:
47
Growth Rate:
85.45%