internetoftim commited on
Commit
7827f5b
1 Parent(s): 2951dde

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -8
README.md CHANGED
@@ -25,26 +25,32 @@ model-index:
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
  should probably proofread and complete it, then remove this comment. -->
27
 
28
- # gqa
 
 
 
 
 
 
29
 
30
- This model is a fine-tuned version of [unc-nlp/lxmert-base-uncased](https://huggingface.co/unc-nlp/lxmert-base-uncased) on the [Graphcore/gqa-lxmert](https://huggingface.co/datasets/Graphcore/gqa-lxmert) dataset.
31
- It achieves the following results on the evaluation set:
32
- - Loss: 1.9326
33
- - Accuracy: 0.5934
34
 
35
  ## Model description
36
 
37
- LXMERT is a transformer model for learning vision-and-language cross-modality representations. It has a Transformer model that has three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. It is pretrained via a combination of masked language modeling, visual-language text alignment, ROI-feature regression, masked visual-attribute modeling, masked visual-object modeling, and visual-question answering objectives. It acheives the state-of-the-art results on VQA anad GQA.
38
 
39
  Paper link : [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://arxiv.org/pdf/1908.07490.pdf)
40
 
41
  ## Intended uses & limitations
42
 
43
- More information needed
 
 
 
 
44
 
45
  ## Training and evaluation data
46
 
47
- [Graphcore/gqa-lxmert](https://huggingface.co/datasets/Graphcore/gqa-lxmert) dataset
48
 
49
  ## Training procedure
50
 
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
  should probably proofread and complete it, then remove this comment. -->
27
 
28
+ # Graphcore/lxmert-gqa-uncased
29
+
30
+ BERT (Bidirectional Encoder Representations from Transformers) is a transformers model which is designed to pretrain bidirectional representations from unlabeled texts. It enables easy and fast fine-tuning for different downstream task such as Sequence Classification, Named Entity Recognition, Question Answering, Multiple Choice and MaskedLM.
31
+
32
+ It was trained with two objectives in pretraining : Masked language modeling(MLM) and Next sentence prediction(NSP). First, MLM is different from traditional LM which sees the words one after another while BERT allows the model to learn a bidirectional representation. In addition to MLM, NSP is used for jointly pertaining text-pair representations.
33
+
34
+ It reduces the need of many engineering efforts for building task specific architectures through pre-trained representation. And achieves state-of-the-art performance on a large suite of sentence-level and token-level tasks.
35
 
 
 
 
 
36
 
37
  ## Model description
38
 
39
+ LXMERT is a transformer model for learning vision-and-language cross-modality representations. It has a Transformer model that has three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. It is pretrained via a combination of masked language modelling, visual-language text alignment, ROI-feature regression, masked visual-attribute modeling, masked visual-object modelling, and visual-question answering objectives. It achieves the state-of-the-art results on VQA anad GQA.
40
 
41
  Paper link : [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://arxiv.org/pdf/1908.07490.pdf)
42
 
43
  ## Intended uses & limitations
44
 
45
+
46
+ This model is a fine-tuned version of [unc-nlp/lxmert-base-uncased](https://huggingface.co/unc-nlp/lxmert-base-uncased) on the [Graphcore/gqa-lxmert](https://huggingface.co/datasets/Graphcore/gqa-lxmert) dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 1.9326
49
+ - Accuracy: 0.5934
50
 
51
  ## Training and evaluation data
52
 
53
+ - [Graphcore/gqa-lxmert](https://huggingface.co/datasets/Graphcore/gqa-lxmert) dataset
54
 
55
  ## Training procedure
56