mrm8488 commited on
Commit
f586274
1 Parent(s): 40b82ca

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -38
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
 
11
  [BERT-Tiny](https://huggingface.co/google/bert_uncased_L-12_H-128_A-2) created by [Google Research](https://github.com/google-research) and fine-tuned on [SQuAD 2.0](https://rajpurkar.github.io/SQuAD-explorer/) for **Q&A** downstream task.
12
 
13
- **Mode size** (after training): **24.3 MB**
14
 
15
  ## Details of BERT-Tiny and its 'family' (from their documentation)
16
 
@@ -38,8 +38,8 @@ The script for fine tuning can be found [here](https://github.com/huggingface/tr
38
 
39
  | Metric | # Value |
40
  | ------ | --------- |
41
- | **EM** | **48.60** |
42
- | **F1** | **49.73** |
43
 
44
 
45
  | Model | EM | F1 score | SIZE (MB) |
@@ -56,8 +56,8 @@ from transformers import pipeline
56
 
57
  qa_pipeline = pipeline(
58
  "question-answering",
59
- model="mrm8488/bert-tiny-finetuned-squadv2",
60
- tokenizer="mrm8488/bert-tiny-finetuned-squadv2"
61
  )
62
 
63
  qa_pipeline({
@@ -65,41 +65,8 @@ qa_pipeline({
65
  'question': "Who has been working hard for hugginface/transformers lately?"
66
 
67
  })
68
-
69
- # Output:
70
- ```
71
-
72
- ```json
73
- {
74
- "answer": "Manuel Romero",
75
- "end": 13,
76
- "score": 0.05684709993458714,
77
- "start": 0
78
- }
79
- ```
80
-
81
- ### Yes! That was easy 🎉 Let's try with another example
82
-
83
- ```python
84
- qa_pipeline({
85
- 'context': "Manuel Romero has been working hardly in the repository hugginface/transformers lately",
86
- 'question': "For which company has worked Manuel Romero?"
87
- })
88
-
89
- # Output:
90
  ```
91
 
92
- ```json
93
- {
94
- "answer": "hugginface/transformers",
95
- "end": 79,
96
- "score": 0.11613431826808274,
97
- "start": 56
98
- }
99
- ```
100
-
101
- ### It works!! 🎉 🎉 🎉
102
-
103
  > Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
104
 
105
  > Made with <span style="color: #e25555;">&hearts;</span> in Spain
 
10
 
11
  [BERT-Tiny](https://huggingface.co/google/bert_uncased_L-12_H-128_A-2) created by [Google Research](https://github.com/google-research) and fine-tuned on [SQuAD 2.0](https://rajpurkar.github.io/SQuAD-explorer/) for **Q&A** downstream task.
12
 
13
+ **Mode size** (after training): **24.33 MB**
14
 
15
  ## Details of BERT-Tiny and its 'family' (from their documentation)
16
 
 
38
 
39
  | Metric | # Value |
40
  | ------ | --------- |
41
+ | **EM** | **57.12** |
42
+ | **F1** | **60.86** |
43
 
44
 
45
  | Model | EM | F1 score | SIZE (MB) |
 
56
 
57
  qa_pipeline = pipeline(
58
  "question-answering",
59
+ model="mrm8488/bert-tiny-5-finetuned-squadv2",
60
+ tokenizer="mrm8488/bert-tiny-5-finetuned-squadv2"
61
  )
62
 
63
  qa_pipeline({
 
65
  'question': "Who has been working hard for hugginface/transformers lately?"
66
 
67
  })
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  ```
69
 
 
 
 
 
 
 
 
 
 
 
 
70
  > Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) | [LinkedIn](https://www.linkedin.com/in/manuel-romero-cs/)
71
 
72
  > Made with <span style="color: #e25555;">&hearts;</span> in Spain