Upload 9 files
Browse files- config.json +50 -0
- l0_module.pt +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- stsb-log.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
- zs.pt +3 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/data/device-aware-bert/token_pruning/teachers/STSB",
|
3 |
+
"architectures": [
|
4 |
+
"ToPBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"do_layer_distill": false,
|
9 |
+
"finetuning_task": "stsb",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"LABEL_0": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"output_attentions": true,
|
28 |
+
"output_hidden_states": true,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"pruned_heads": {
|
32 |
+
"0": [],
|
33 |
+
"1": [],
|
34 |
+
"2": [],
|
35 |
+
"3": [],
|
36 |
+
"4": [],
|
37 |
+
"5": [],
|
38 |
+
"6": [],
|
39 |
+
"7": [],
|
40 |
+
"8": [],
|
41 |
+
"9": [],
|
42 |
+
"10": [],
|
43 |
+
"11": []
|
44 |
+
},
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.16.0",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 30522
|
50 |
+
}
|
l0_module.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e41e2b285353feb1c1094cb8da542b7dddb51add65726e952fb743e4cdd6f5a
|
3 |
+
size 6171
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ab711f1a09c92a6feadf6a70bc39e8b2f7b08398c033cd2fe0312b3ad3a1710
|
3 |
+
size 438016173
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
stsb-log.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/mnt/data/device-aware-bert/token_pruning/teachers/STSB", "tokenizer_class": "BertTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
zs.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b8b852a971505c25aece5a697ef2f828f3f818c93bc11a7ac62d192019dd4f3
|
3 |
+
size 2023
|