cyanic-selkie commited on
Commit
d98f98f
1 Parent(s): 10acddc

Reverts an accidental push.

Browse files
.gitattributes CHANGED
@@ -33,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
- tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "cyanic-selkie/nexus-mapper-roberta-xlm-512-cos-wikianc",
3
  "architectures": [
4
  "ELModel"
5
  ],
@@ -20,12 +20,11 @@
20
  "num_hidden_layers": 12,
21
  "output_attentions": true,
22
  "output_hidden_states": true,
23
- "output_past": true,
24
  "pad_token_id": 1,
25
  "position_embedding_type": "absolute",
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.33.2",
28
  "type_vocab_size": 1,
29
  "use_cache": true,
30
- "vocab_size": 250002
31
  }
 
1
  {
2
+ "_name_or_path": "models/nexus-mapper-roberta-en-512-cos-wikianc-conll/checkpoint-1370/",
3
  "architectures": [
4
  "ELModel"
5
  ],
 
20
  "num_hidden_layers": 12,
21
  "output_attentions": true,
22
  "output_hidden_states": true,
 
23
  "pad_token_id": 1,
24
  "position_embedding_type": "absolute",
25
  "torch_dtype": "float32",
26
  "transformers_version": "4.33.2",
27
  "type_vocab_size": 1,
28
  "use_cache": true,
29
+ "vocab_size": 50265
30
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4210f6ab4dc9c8f9c90a89b3138879406863bef5ead87fbf44353d04402b74d
3
- size 1114081465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf25dbfb53bff1a0334e2aaf3caea6cd4c8301b5aa9df2d2d883213100d80424
3
+ size 500489401
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,22 +1,18 @@
1
  {
 
2
  "bos_token": "<s>",
3
  "clean_up_tokenization_spaces": true,
4
  "cls_token": "<s>",
5
  "eos_token": "</s>",
6
- "mask_token": {
7
- "__type": "AddedToken",
8
- "content": "<mask>",
9
- "lstrip": true,
10
- "normalized": true,
11
- "rstrip": false,
12
- "single_word": false
13
- },
14
  "max_length": 512,
15
  "model_max_length": 512,
16
  "pad_token": "<pad>",
17
  "sep_token": "</s>",
18
  "stride": 256,
19
- "tokenizer_class": "XLMRobertaTokenizer",
 
20
  "truncation_side": "right",
21
  "truncation_strategy": "longest_first",
22
  "unk_token": "<unk>"
 
1
  {
2
+ "add_prefix_space": false,
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
 
 
 
 
 
 
9
  "max_length": 512,
10
  "model_max_length": 512,
11
  "pad_token": "<pad>",
12
  "sep_token": "</s>",
13
  "stride": 256,
14
+ "tokenizer_class": "RobertaTokenizer",
15
+ "trim_offsets": true,
16
  "truncation_side": "right",
17
  "truncation_strategy": "longest_first",
18
  "unk_token": "<unk>"