aertoria commited on
Commit
41c44b0
1 Parent(s): bb38c6b

Upload fine-tuned model

Browse files
Files changed (7) hide show
  1. .DS_Store +0 -0
  2. config.json +1 -1
  3. merges.txt +1 -1
  4. special_tokens_map.json +51 -1
  5. tf_model.h5 +1 -1
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +60 -1
.DS_Store ADDED
Binary file (6.15 kB). View file
 
config.json CHANGED
@@ -262,7 +262,7 @@
262
  "position_biased_input": false,
263
  "relative_attention": true,
264
  "torch_dtype": "float32",
265
- "transformers_version": "4.11.3",
266
  "type_vocab_size": 0,
267
  "vocab_size": 50265
268
  }
 
262
  "position_biased_input": false,
263
  "relative_attention": true,
264
  "torch_dtype": "float32",
265
+ "transformers_version": "4.44.2",
266
  "type_vocab_size": 0,
267
  "vocab_size": 50265
268
  }
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
special_tokens_map.json CHANGED
@@ -1 +1,51 @@
1
- {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7988d4a43809d39802ad244fad532df4d5fb5e7e2c6944c77b499745c8cf86d3
3
  size 555049352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2453f28682f682e5ac42538fbacb268aaa93af95e669346217b67a9837cc4b
3
  size 555049352
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,60 @@
1
- {"unk_token": "[UNK]", "bos_token": "[CLS]", "eos_token": "[SEP]", "add_prefix_space": true, "errors": "replace", "sep_token": "[SEP]", "cls_token": "[CLS]", "pad_token": "[PAD]", "mask_token": "[MASK]", "add_bos_token": false, "added_tokens_decoder": {"0": {"content": "[PAD]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "[CLS]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "[SEP]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "3": {"content": "[UNK]", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "50264": {"content": "[MASK]", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true}}, "additional_special_tokens": [], "clean_up_tokenization_spaces": true, "do_lower_case": false, "model_max_length": 512, "vocab_type": "gpt2", "special_tokens_map_file": "/root/.cache/huggingface/transformers/32f17add6ed2d81439ebbc3ea70cdbf81f77aa6dfd846cbc050383fd38f928c6.33ea9968fa7ac107543fcd0be7da0a5b475c882cb5390b8ce2fc4a0c34fe4d6b", "name_or_path": "lakshyakh93/deberta_finetuned_pii", "tokenizer_class": "DebertaTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": true,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "[PAD]",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "[SEP]",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "[UNK]",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "50264": {
38
+ "content": "[MASK]",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "additional_special_tokens": [],
47
+ "bos_token": "[CLS]",
48
+ "clean_up_tokenization_spaces": true,
49
+ "cls_token": "[CLS]",
50
+ "do_lower_case": false,
51
+ "eos_token": "[SEP]",
52
+ "errors": "replace",
53
+ "mask_token": "[MASK]",
54
+ "model_max_length": 512,
55
+ "pad_token": "[PAD]",
56
+ "sep_token": "[SEP]",
57
+ "tokenizer_class": "DebertaTokenizer",
58
+ "unk_token": "[UNK]",
59
+ "vocab_type": "gpt2"
60
+ }