add model and tokenizer
Browse files- config.json +41 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "unc-nlp/lxmert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"LxmertForPreTraining"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 3072,
|
12 |
+
"l_layers": 9,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "lxmert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_attr_labels": 400,
|
18 |
+
"num_hidden_layers": {
|
19 |
+
"cross_encoder": 5,
|
20 |
+
"language": 9,
|
21 |
+
"vision": 5
|
22 |
+
},
|
23 |
+
"num_object_labels": 1600,
|
24 |
+
"num_qa_labels": 9500,
|
25 |
+
"r_layers": 5,
|
26 |
+
"task_mask_lm": true,
|
27 |
+
"task_matched": true,
|
28 |
+
"task_obj_predict": true,
|
29 |
+
"task_qa": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.18.0",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"visual_attr_loss": true,
|
34 |
+
"visual_feat_dim": 2048,
|
35 |
+
"visual_feat_loss": true,
|
36 |
+
"visual_loss_normalizer": 6.67,
|
37 |
+
"visual_obj_loss": true,
|
38 |
+
"visual_pos_dim": 4,
|
39 |
+
"vocab_size": 30522,
|
40 |
+
"x_layers": 5
|
41 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f85d32473cd475f30f94e685265b5c1ecffc72419f61fd4689f9cc7c4bd252b6
|
3 |
+
size 912372921
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "model_max_length": 512, "special_tokens_map_file": "/home/eltoto/unc-nlp/special_tokens_map.json", "full_tokenizer_file": null}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|