xinhe commited on
Commit
533f50a
1 Parent(s): 4a3c353

add int8 embedding

Browse files
Files changed (5) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +6 -4
  4. tokenizer_config.json +1 -1
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/home2/xinhe/intel-model-mrpc/roberta-base-mrpc/",
3
  "architectures": [
4
  "RobertaForSequenceClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "Intel/roberta-base-mrpc",
3
  "architectures": [
4
  "RobertaForSequenceClassification"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40946530ea1bb6a7889d32b0aed23e9f2ba0a407fe9e68f20ccaf6269a45ea19
3
- size 127033837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d78079577f379740987673369c23a05dbf9425fd406e763783b2966669e99b
3
+ size 127038057
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 256,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 256
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
@@ -67,7 +67,8 @@
67
  "pre_tokenizer": {
68
  "type": "ByteLevel",
69
  "add_prefix_space": false,
70
- "trim_offsets": true
 
71
  },
72
  "post_processor": {
73
  "type": "RobertaProcessing",
@@ -85,7 +86,8 @@
85
  "decoder": {
86
  "type": "ByteLevel",
87
  "add_prefix_space": true,
88
- "trim_offsets": true
 
89
  },
90
  "model": {
91
  "type": "BPE",
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 128
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
67
  "pre_tokenizer": {
68
  "type": "ByteLevel",
69
  "add_prefix_space": false,
70
+ "trim_offsets": true,
71
+ "use_regex": true
72
  },
73
  "post_processor": {
74
  "type": "RobertaProcessing",
 
86
  "decoder": {
87
  "type": "ByteLevel",
88
  "add_prefix_space": true,
89
+ "trim_offsets": true,
90
+ "use_regex": true
91
  },
92
  "model": {
93
  "type": "BPE",
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home2/xinhe/intel-model-mrpc/roberta-base-mrpc/", "tokenizer_class": "RobertaTokenizer"}
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Intel/roberta-base-mrpc", "tokenizer_class": "RobertaTokenizer"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff