model documentation

#2
by nazneen - opened
Files changed (1) hide show
  1. README.md +165 -6
README.md CHANGED
@@ -1,15 +1,174 @@
 
1
  ---
2
- language: "en"
 
3
  datasets:
4
  - squad
5
  metrics:
6
  - squad
7
- license: apache-2.0
8
  ---
9
 
10
- # ONNX Conversion of [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
 
12
- # DistilBERT base cased distilled SQuAD
 
 
 
 
 
 
 
 
13
 
14
- This model is a fine-tune checkpoint of [DistilBERT-base-cased](https://huggingface.co/distilbert-base-cased), fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.
15
- This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
 
1
+
2
  ---
3
+ language: en
4
+ license: apache-2.0
5
  datasets:
6
  - squad
7
  metrics:
8
  - squad
 
9
  ---
10
 
11
+ # Model Card for ONNX Conversion of distilbert-base-cased-distilled-squad
12
+
13
+ # Model Details
14
+
15
+ ## Model Description
16
+ This model is a fine-tune checkpoint of DistilBERT-base-cased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1.
17
+
18
+ - **Developed by:** Philipp Schmid
19
+ - **Shared by [Optional]:** Hugging Face
20
+ - **Model type:** Question Answering
21
+ - **Language(s) (NLP):** en
22
+ - **License:** Apache-2.0
23
+ - **Related Models:** [distilbert-base-cased-distilled-squad](https://huggingface.co/distilbert-base-cased-distilled-squad)
24
+ - **Parent Model:** distilbert
25
+ - **Resources for more information:**
26
+ - [Space](https://huggingface.co/spaces/krrishD/philschmid_distilbert-onnx)
27
+ - [Blog Post](https://www.philschmid.de/convert-transformers-to-onnx)
28
+
29
+ # Uses
30
+
31
+
32
+ ## Direct Use
33
+
34
+ This model can be used for question answering.
35
+
36
+ ## Downstream Use [Optional]
37
+
38
+
39
+ More information needed.
40
+
41
+
42
+ ## Out-of-Scope Use
43
+
44
+
45
+ The model should not be used to intentionally create hostile or alienating environments for people.
46
+
47
+ # Bias, Risks, and Limitations
48
+
49
+ Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups.
50
+
51
+
52
+ ## Recommendations
53
+
54
+
55
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
56
+
57
+
58
+ # Training Details
59
+
60
+ ## Training Data
61
+
62
+ To learn more about the SQuAD v1.1 dataset, see the associated [SQuAD v1.1 dataset card](https://huggingface.co/datasets/squad) for further details.
63
+
64
+ ## Training Procedure
65
+
66
+
67
+ ### Preprocessing
68
+
69
+ See the [distilbert-base-cased model card](https://huggingface.co/distilbert-base-cased) for further details.
70
+
71
+ ### Speeds, Sizes, Times
72
+
73
+
74
+ See the [distilbert-base-cased model card](https://huggingface.co/distilbert-base-cased) for further details.
75
+
76
+ # Evaluation
77
+
78
+
79
+
80
+ ## Testing Data, Factors & Metrics
81
+
82
+ ### Testing Data
83
+
84
+
85
+ More information needed
86
+
87
+ ### Factors
88
+
89
+
90
+ ### Metrics
91
+
92
+ More information needed
93
+
94
+ ## Results
95
+
96
+ This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
97
+
98
+ # Model Examination
99
+ More information needed
100
+
101
+ # Environmental Impact
102
+
103
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
104
+
105
+ - **Hardware Type:** More information needed
106
+ - **Hours used:** More information needed
107
+ - **Cloud Provider:** More information needed
108
+ - **Compute Region:** More information needed
109
+ - **Carbon Emitted:** More information needed
110
+
111
+ # Technical Specifications [optional]
112
+
113
+ ## Model Architecture and Objective
114
+
115
+ More information needed
116
+
117
+ ## Compute Infrastructure
118
+
119
+ More information needed
120
+
121
+ ### Hardware
122
+
123
+ More information needed
124
+
125
+ ### Software
126
+
127
+ More information needed
128
+
129
+ # Citation
130
+
131
+
132
+ **BibTeX:**
133
+
134
+ More information needed
135
+
136
+ **APA:**
137
+
138
+ More information needed
139
+
140
+ # Glossary [optional]
141
+
142
+ 1. What is ONNX?
143
+ The ONNX (Open Neural Network eXchange) is an open standard and format to represent machine learning models. ONNX defines a common set of operators and a common file format to represent deep learning models in a wide variety of frameworks, including PyTorch and TensorFlow.
144
+
145
+
146
+ # More Information [optional]
147
+
148
+ More information needed
149
+
150
+ # Model Card Authors [optional]
151
+
152
+ Philipp Schmid in collaboration with Ezi Ozoani and the Hugging Face team.
153
+
154
+ # Model Card Contact
155
+
156
+ More information needed
157
+
158
+ # How to Get Started with the Model
159
+
160
+ Use the code below to get started with the model.
161
+
162
+ <details>
163
+ <summary> Click to expand </summary>
164
 
165
+ ```python
166
+ from transformers import AutoTokenizer, AutoModelForQuestionAnswering
167
+
168
+ tokenizer = AutoTokenizer.from_pretrained("philschmid/distilbert-onnx")
169
+
170
+ model = AutoModelForQuestionAnswering.from_pretrained("philschmid/distilbert-onnx")
171
+
172
+ ```
173
+ </details>
174