model documentation
Browse files
README.md
ADDED
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language: en
|
3 |
+
tags:
|
4 |
+
- text-classification
|
5 |
+
- albert
|
6 |
+
---
|
7 |
+
|
8 |
+
# Model Card for albert-base-rci-wikisql-col
|
9 |
+
|
10 |
+
# Model Details
|
11 |
+
|
12 |
+
## Model Description
|
13 |
+
|
14 |
+
More information needed
|
15 |
+
|
16 |
+
- **Developed by:** Michael Glass
|
17 |
+
- **Shared by [Optional]:** Michael Glass
|
18 |
+
|
19 |
+
- **Model type:** Token Classification
|
20 |
+
- **Language(s) (NLP):** English
|
21 |
+
- **License:** More information needed
|
22 |
+
- **Parent Model:** [ALBERT Base v2](https://huggingface.co/albert-base-v2?text=The+goal+of+life+is+%5BMASK%5D.)
|
23 |
+
- **Resources for more information:**
|
24 |
+
- [ALBERT Base GitHub Repo](https://github.com/jhyuklee/biobert)
|
25 |
+
- [ALBERT Base Paper](https://github.com/google-research/albert)
|
26 |
+
|
27 |
+
# Uses
|
28 |
+
|
29 |
+
|
30 |
+
## Direct Use
|
31 |
+
This model can be used for the task of text classification.
|
32 |
+
> This model is primarily aimed at being fine-tuned on tasks that use the whole sentence (potentially masked) to make decisions, such as sequence classification, token classification or question answering.
|
33 |
+
|
34 |
+
See [ALBERT Base v2 model card](https://huggingface.co/albert-base-v2?text=The+goal+of+life+is+%5BMASK%5D.) for more information.
|
35 |
+
|
36 |
+
|
37 |
+
## Downstream Use [Optional]
|
38 |
+
|
39 |
+
More information needed.
|
40 |
+
|
41 |
+
## Out-of-Scope Use
|
42 |
+
|
43 |
+
The model should not be used to intentionally create hostile or alienating environments for people.
|
44 |
+
|
45 |
+
For tasks such as text generation you should look at model like GPT2.
|
46 |
+
|
47 |
+
# Bias, Risks, and Limitations
|
48 |
+
|
49 |
+
|
50 |
+
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.
|
51 |
+
|
52 |
+
|
53 |
+
|
54 |
+
## Recommendations
|
55 |
+
|
56 |
+
|
57 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
58 |
+
|
59 |
+
# Training Details
|
60 |
+
|
61 |
+
## Training Data
|
62 |
+
The ALBERT model was pretrained on [BookCorpus](https://yknzhu.wixsite.com/mbweb), a dataset consisting of 11,038 unpublished books and [English] Wikipedia(https://en.wikipedia.org/wiki/English_Wikipedia) (excluding lists, tables and headers).
|
63 |
+
See [ALBERT Base v2 model card](https://huggingface.co/albert-base-v2?text=The+goal+of+life+is+%5BMASK%5D.) for more information.
|
64 |
+
|
65 |
+
## Training Procedure
|
66 |
+
|
67 |
+
|
68 |
+
### Preprocessing
|
69 |
+
|
70 |
+
>The texts are lowercased and tokenized using SentencePiece and a vocabulary size of 30,000. The inputs of the model are
|
71 |
+
then of the form:
|
72 |
+
|
73 |
+
```
|
74 |
+
[CLS] Sentence A [SEP] Sentence B [SEP]
|
75 |
+
```
|
76 |
+
See [ALBERT Base v2 model card](https://huggingface.co/albert-base-v2?text=The+goal+of+life+is+%5BMASK%5D.) for more information.
|
77 |
+
|
78 |
+
|
79 |
+
|
80 |
+
|
81 |
+
### Speeds, Sizes, Times
|
82 |
+
|
83 |
+
More information needed
|
84 |
+
|
85 |
+
|
86 |
+
|
87 |
+
# Evaluation
|
88 |
+
|
89 |
+
|
90 |
+
## Testing Data, Factors & Metrics
|
91 |
+
|
92 |
+
### Testing Data
|
93 |
+
|
94 |
+
More information needed
|
95 |
+
|
96 |
+
### Factors
|
97 |
+
More information needed
|
98 |
+
|
99 |
+
### Metrics
|
100 |
+
|
101 |
+
More information needed
|
102 |
+
|
103 |
+
|
104 |
+
## Results
|
105 |
+
|
106 |
+
More information needed
|
107 |
+
|
108 |
+
|
109 |
+
# Model Examination
|
110 |
+
|
111 |
+
More information needed
|
112 |
+
|
113 |
+
# Environmental Impact
|
114 |
+
|
115 |
+
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).
|
116 |
+
|
117 |
+
- **Hardware Type:** More information needed
|
118 |
+
- **Hours used:** More information needed
|
119 |
+
- **Cloud Provider:** More information needed
|
120 |
+
- **Compute Region:** More information needed
|
121 |
+
- **Carbon Emitted:** More information needed
|
122 |
+
|
123 |
+
# Technical Specifications [optional]
|
124 |
+
|
125 |
+
## Model Architecture and Objective
|
126 |
+
|
127 |
+
More information needed
|
128 |
+
|
129 |
+
## Compute Infrastructure
|
130 |
+
|
131 |
+
More information needed
|
132 |
+
|
133 |
+
### Hardware
|
134 |
+
|
135 |
+
|
136 |
+
More information needed
|
137 |
+
|
138 |
+
### Software
|
139 |
+
|
140 |
+
More information needed.
|
141 |
+
|
142 |
+
# Citation
|
143 |
+
|
144 |
+
|
145 |
+
**BibTeX:**
|
146 |
+
|
147 |
+
```bibtex
|
148 |
+
@article{DBLP:journals/corr/abs-1909-11942,
|
149 |
+
author = {Zhenzhong Lan and
|
150 |
+
Mingda Chen and
|
151 |
+
Sebastian Goodman and
|
152 |
+
Kevin Gimpel and
|
153 |
+
Piyush Sharma and
|
154 |
+
Radu Soricut},
|
155 |
+
title = {{ALBERT:} {A} Lite {BERT} for Self-supervised Learning of Language
|
156 |
+
Representations},
|
157 |
+
journal = {CoRR},
|
158 |
+
volume = {abs/1909.11942},
|
159 |
+
year = {2019},
|
160 |
+
url = {http://arxiv.org/abs/1909.11942},
|
161 |
+
archivePrefix = {arXiv},
|
162 |
+
eprint = {1909.11942},
|
163 |
+
timestamp = {Fri, 27 Sep 2019 13:04:21 +0200},
|
164 |
+
biburl = {https://dblp.org/rec/journals/corr/abs-1909-11942.bib},
|
165 |
+
bibsource = {dblp computer science bibliography, https://dblp.org}
|
166 |
+
}
|
167 |
+
```
|
168 |
+
|
169 |
+
|
170 |
+
|
171 |
+
|
172 |
+
|
173 |
+
**APA:**
|
174 |
+
|
175 |
+
More information needed
|
176 |
+
|
177 |
+
# Glossary [optional]
|
178 |
+
|
179 |
+
More information needed
|
180 |
+
|
181 |
+
# More Information [optional]
|
182 |
+
More information needed
|
183 |
+
|
184 |
+
# Model Card Authors [optional]
|
185 |
+
|
186 |
+
Michael Glass in collaboration with Ezi Ozoani and the Hugging Face team
|
187 |
+
|
188 |
+
# Model Card Contact
|
189 |
+
|
190 |
+
More information needed
|
191 |
+
|
192 |
+
# How to Get Started with the Model
|
193 |
+
|
194 |
+
Use the code below to get started with the model.
|
195 |
+
|
196 |
+
<details>
|
197 |
+
<summary> Click to expand </summary>
|
198 |
+
|
199 |
+
```python
|
200 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
201 |
+
|
202 |
+
tokenizer = AutoTokenizer.from_pretrained("michaelrglass/albert-base-rci-wikisql-col")
|
203 |
+
|
204 |
+
model = AutoModelForSequenceClassification.from_pretrained("michaelrglass/albert-base-rci-wikisql-col")
|
205 |
+
```
|
206 |
+
</details>
|