model documentation
#2
by
nazneen
- opened
README.md
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: cc-by-nc-4.0
|
5 |
+
---
|
6 |
+
# Model Card for bert-small-mm_retrieval-passage_encoder
|
7 |
+
|
8 |
+
|
9 |
+
# Model Details
|
10 |
+
|
11 |
+
## Model Description
|
12 |
+
|
13 |
+
Multilingual DPR Model base on bert-base-multilingual-cased.
|
14 |
+
|
15 |
+
- **Developed by:** Deepset
|
16 |
+
- **Shared by [Optional]:** Hugging Face
|
17 |
+
- **Model type:** dpr
|
18 |
+
- **Language(s) (NLP):** english
|
19 |
+
- **License:** CC-BY-NC 4.0
|
20 |
+
- **Related Models:**
|
21 |
+
- **Parent Model:** DPR
|
22 |
+
- **Resources for more information:**
|
23 |
+
- [GitHub Repo](https://github.com/facebookresearch/DPR)
|
24 |
+
- [Associated Paper](https://arxiv.org/abs/2004.04906)
|
25 |
+
|
26 |
+
|
27 |
+
# Uses
|
28 |
+
|
29 |
+
|
30 |
+
## Direct Use
|
31 |
+
|
32 |
+
This model can be used for the task of Question Answering
|
33 |
+
|
34 |
+
## Downstream Use [Optional]
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Out-of-Scope Use
|
39 |
+
|
40 |
+
The model should not be used to intentionally create hostile or alienating environments for people.
|
41 |
+
|
42 |
+
# Bias, Risks, and Limitations
|
43 |
+
|
44 |
+
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.
|
45 |
+
|
46 |
+
|
47 |
+
## Recommendations
|
48 |
+
|
49 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
50 |
+
|
51 |
+
|
52 |
+
# Training Details
|
53 |
+
|
54 |
+
## Training Data
|
55 |
+
|
56 |
+
The English Wikipedia dump from Dec. 20, 2018 as the source documents for answering questions
|
57 |
+
|
58 |
+
## Training Procedure
|
59 |
+
|
60 |
+
### Preprocessing
|
61 |
+
|
62 |
+
The model creators note in the [associated paper](https://arxiv.org/pdf/2004.04906.pdf)
|
63 |
+
> We first apply the pre-processing code released in DrQA (Chen et al., 2017) to extract the clean, text-portion of articles from the Wikipedia dump.
|
64 |
+
|
65 |
+
### Speeds, Sizes, Times
|
66 |
+
|
67 |
+
More information needed
|
68 |
+
|
69 |
+
# Evaluation
|
70 |
+
|
71 |
+
|
72 |
+
## Testing Data, Factors & Metrics
|
73 |
+
|
74 |
+
### Testing Data
|
75 |
+
|
76 |
+
More information needed
|
77 |
+
|
78 |
+
### Factors
|
79 |
+
|
80 |
+
|
81 |
+
### Metrics
|
82 |
+
|
83 |
+
More information needed
|
84 |
+
## Results
|
85 |
+
|
86 |
+
More information needed
|
87 |
+
|
88 |
+
# Model Examination
|
89 |
+
|
90 |
+
More information needed
|
91 |
+
|
92 |
+
# Environmental Impact
|
93 |
+
|
94 |
+
|
95 |
+
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).
|
96 |
+
|
97 |
+
- **Hardware Type:** 8 x 32GB GPUs
|
98 |
+
- **Hours used:** More information needed
|
99 |
+
- **Cloud Provider:** More information needed
|
100 |
+
- **Compute Region:** More information needed
|
101 |
+
- **Carbon Emitted:** More information needed
|
102 |
+
|
103 |
+
# Technical Specifications [optional]
|
104 |
+
|
105 |
+
## Model Architecture and Objective
|
106 |
+
|
107 |
+
DPRContextEncoder
|
108 |
+
|
109 |
+
## Compute Infrastructure
|
110 |
+
|
111 |
+
More information needed
|
112 |
+
|
113 |
+
### Hardware
|
114 |
+
|
115 |
+
More information needed
|
116 |
+
|
117 |
+
### Software
|
118 |
+
transformers_version: 4.7.0
|
119 |
+
|
120 |
+
# Citation
|
121 |
+
|
122 |
+
|
123 |
+
**BibTeX:**
|
124 |
+
```
|
125 |
+
@inproceedings{karpukhin-etal-2020-dense,
|
126 |
+
title = "Dense Passage Retrieval for Open-Domain Question Answering",
|
127 |
+
author = "Karpukhin, Vladimir and Oguz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau",
|
128 |
+
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
|
129 |
+
month = nov,
|
130 |
+
year = "2020",
|
131 |
+
address = "Online",
|
132 |
+
publisher = "Association for Computational Linguistics",
|
133 |
+
url = "https://www.aclweb.org/anthology/2020.emnlp-main.550",
|
134 |
+
doi = "10.18653/v1/2020.emnlp-main.550",
|
135 |
+
pages = "6769--6781",
|
136 |
+
}
|
137 |
+
|
138 |
+
```
|
139 |
+
|
140 |
+
|
141 |
+
# Glossary [optional]
|
142 |
+
More information needed
|
143 |
+
|
144 |
+
# More Information [optional]
|
145 |
+
|
146 |
+
More information needed
|
147 |
+
|
148 |
+
# Model Card Authors [optional]
|
149 |
+
|
150 |
+
|
151 |
+
Deepset in collaboration with Ezi Ozoani and the Hugging Face team
|
152 |
+
|
153 |
+
# Model Card Contact
|
154 |
+
|
155 |
+
More information needed
|
156 |
+
|
157 |
+
# How to Get Started with the Model
|
158 |
+
|
159 |
+
Use the code below to get started with the model.
|
160 |
+
|
161 |
+
<details>
|
162 |
+
<summary> Click to expand </summary>
|
163 |
+
|
164 |
+
```python
|
165 |
+
from transformers import AutoTokenizer, DPRContextEncoder
|
166 |
+
|
167 |
+
tokenizer = AutoTokenizer.from_pretrained("deepset/bert-small-mm_retrieval-passage_encoder")
|
168 |
+
|
169 |
+
model = DPRContextEncoder.from_pretrained("deepset/bert-small-mm_retrieval-passage_encoder")
|
170 |
+
|
171 |
+
```
|
172 |
+
</details>
|