Jingbiao commited on
Commit
2267cff
1 Parent(s): 314f92c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -167
README.md CHANGED
@@ -1,199 +1,73 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
4
  ---
5
 
6
- # Model Card for Model ID
7
 
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
11
-
12
- ## Model Details
13
 
14
  ### Model Description
15
 
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
-
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
 
28
- ### Model Sources [optional]
29
 
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** https://arxiv.org/abs/2402.08327
34
- - **Demo [optional]:** [More Information Needed]
35
 
36
  ## Uses
37
 
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
  ### Direct Use
41
 
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
 
44
- [More Information Needed]
45
 
46
- ### Downstream Use [optional]
47
 
48
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
 
50
- [More Information Needed]
51
-
52
- ### Out-of-Scope Use
53
-
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
-
58
- ## Bias, Risks, and Limitations
59
-
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
-
64
- ### Recommendations
65
-
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
  ## How to Get Started with the Model
71
 
72
- Use the code below to get started with the model.
73
-
74
- [More Information Needed]
75
-
76
- ## Training Details
77
-
78
- ### Training Data
79
-
80
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
-
82
- [More Information Needed]
83
-
84
- ### Training Procedure
85
-
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
-
88
- #### Preprocessing [optional]
89
-
90
- [More Information Needed]
91
-
92
-
93
- #### Training Hyperparameters
94
-
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
-
97
- #### Speeds, Sizes, Times [optional]
98
-
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
-
101
- [More Information Needed]
102
-
103
- ## Evaluation
104
-
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
-
107
- ### Testing Data, Factors & Metrics
108
-
109
- #### Testing Data
110
-
111
- <!-- This should link to a Dataset Card if possible. -->
112
 
113
- [More Information Needed]
 
 
 
 
114
 
115
- #### Factors
116
 
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
 
119
- [More Information Needed]
 
 
 
 
 
 
120
 
121
- #### Metrics
122
 
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
 
125
- [More Information Needed]
126
-
127
- ### Results
128
-
129
- [More Information Needed]
130
-
131
- #### Summary
132
-
133
-
134
-
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
-
141
- ## Environmental Impact
142
-
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
-
145
- - **Hardware Type:** [More Information Needed]
146
- - **Hours used:** [More Information Needed]
147
- - **Cloud Provider:** [More Information Needed]
148
- - **Compute Region:** [More Information Needed]
149
- - **Carbon Emitted:** [More Information Needed]
150
-
151
- ## Technical Specifications [optional]
152
-
153
- ### Model Architecture and Objective
154
-
155
- [More Information Needed]
156
-
157
- ### Compute Infrastructure
158
-
159
- [More Information Needed]
160
-
161
- #### Hardware
162
-
163
- [More Information Needed]
164
-
165
- #### Software
166
-
167
- [More Information Needed]
168
-
169
- ## Citation [optional]
170
-
171
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
172
 
173
  **BibTeX:**
174
-
175
- [More Information Needed]
176
-
177
- **APA:**
178
-
179
- [More Information Needed]
180
-
181
- ## Glossary [optional]
182
-
183
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
184
-
185
- [More Information Needed]
186
-
187
- ## More Information [optional]
188
-
189
- [More Information Needed]
190
-
191
- ## Model Card Authors [optional]
192
-
193
- [More Information Needed]
194
-
195
- ## Model Card Contact
196
-
197
- [More Information Needed]
198
-
199
-
 
1
  ---
2
  library_name: transformers
3
+ license: mit
4
+ language:
5
+ - en
6
  ---
7
 
8
+ # PreFLMR model card
9
 
 
 
 
 
 
10
 
11
  ### Model Description
12
 
13
+ - **Model type:** PreFLMR is an open-source model for multimodal knowledge retrieval. It is a transformer-based model that uses a combination of text and image inputs to retrieve relevant documents from a large corpus.
14
+ - **Language(s) (NLP):** English
15
+ - **License:** MIT License
 
 
 
 
 
 
 
 
16
 
17
+ ### Paper and resources for more detail
18
 
19
+ - **Blog Post for quick overview:** https://www.jinghong-chen.net/preflmr-sota-open-sourced-multi/
20
+ - **Paper:** https://arxiv.org/abs/2402.08327
21
+ - **Gradio Demo:** https://u60544-b8d4-53eaa55d.westx.seetacloud.com:8443/
22
+ - **Repository:** https://github.com/LinWeizheDragon/FLMR
23
+ - **Project Page:** https://preflmr.github.io/
24
 
25
  ## Uses
26
 
 
 
27
  ### Direct Use
28
 
 
29
 
30
+ This model can be used directly to retrieve documents from a large corpus using a combination of text and image input queries. The retrieval useage can be found in the [official implementation](https://github.com/LinWeizheDragon/FLMR).
31
 
32
+ ### Downstream Use
33
 
34
  <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
35
 
36
+ This model can be used combined with language models to create a retrieval-augmented language model. The useage for Knowledge-based VQA can be found in [RAVQA](https://github.com/linweizhedragon/retrieval-augmented-visual-question-answering)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
 
38
  ## How to Get Started with the Model
39
 
40
+ For details of training, indexing and performing retrieval, please refer to [here](https://github.com/LinWeizheDragon/FLMR).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
 
42
+ ## Training datasets
43
+ The model is pretrained on three types of tasks with a total of nine datasets:
44
+ 1. Image to Text retrieval: WIT, KVQA and CC3M
45
+ 2. Question to Text retrieval: MSMARCO
46
+ 3. Image & Question to Text retrieval: LLaVA, OVEN, OKVQA, Infoseek and E-VQA
47
 
48
+ These datasets were converted to retrieval format. For details on the dataset split and conversion process, please refer to the paper [PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers](https://arxiv.org/abs/2402.08327). We will release the proprocessed datasets soon.
49
 
 
50
 
51
+ ## Evaluation datasets
52
+ We evaluate our models on WIT, LLaVA, OVEN, KVQA, IGLUE (subset of WIT), Infoseek, E-VQA, OKVQA and MSMARCO.
53
+ | Model | Vision Encoder | Text Encoder | Checkpoint Name | No. Param. | WIT | LLaVA | OVEN | KVQA | IGLUE | Infoseek | E-VQA | OKVQA | MSMARCO |
54
+ |---------|----------------|--------------|-------------------------------------------------------------|-------|-------|--------|-------|-------|-------|----------|-------|--------|-------|
55
+ | PreFLMR | ViT-B | Base-v2 | [LinWeizheDragon/PreFLMR_ViT-B](https://huggingface.co/LinWeizheDragon/PreFLMR_ViT-B) | 327M | 41.7 | 67.2 | 46.3 | 28.6 | 57.3 | 48.8 | 67.9 | 66.1 | 79.5 |
56
+ | PreFLMR | ViT-L | Base-v2 | [LinWeizheDragon/PreFLMR_ViT-L](https://huggingface.co/LinWeizheDragon/PreFLMR_ViT-L) | 543M | 60.5 | 71.8 | 59.8 | 43.6 | 69.2 | 57.9 | 70.8 | 68.5 | 78.7 |
57
+ | PreFLMR | ViT-G | Base-v2 | [LinWeizheDragon/PreFLMR_ViT-G](https://huggingface.co/LinWeizheDragon/PreFLMR_ViT-G) | 2.1B | 61.5 | 72.4 | 63.4 | 42.1 |71.5 | 59.6 | 73.1 | 68.6 | 78.6 |
58
 
59
+ For the evaluation metrics, WIT uses Recall@10, IGLUE uses Recall@1, and all the rest datasets use Recall@5.
60
 
 
61
 
62
+ ## Citation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
 
64
  **BibTeX:**
65
+ ```
66
+ @article{Lin_Mei_Chen_Byrne_2024,
67
+ title={PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers},
68
+ url={http://arxiv.org/abs/2402.08327},
69
+ number={arXiv:2402.08327},
70
+ publisher={arXiv},
71
+ author={Lin, Weizhe and Mei, Jingbiao and Chen, Jinghong and Byrne, Bill},
72
+ year={2024}}
73
+ ```