Hugging Face's logo

RPygramar
/
monolang_gpt2

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
RPygramar commited on
Commit
db64a2d
·
verified ·
1 Parent(s): 1f386ea

End of training

Browse files
Files changed (8) hide show
  1. README.md +0 -0
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. special_tokens_map.json +6 -20
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +7 -14
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54c44ad129d0742df3468019b4b590ed4e2d2e2a5a8da5775a536720c6ab1ca2
3
  size 503128704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ceb8575bbfd8c1a2f5fd53a549fd8f5f8e89954dbd51e4b189c65c6b19e9af
3
  size 503128704
special_tokens_map.json CHANGED
@@ -2,49 +2,35 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "eos_token": {
17
  "content": "</s>",
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": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
- "content": "</s>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
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
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
 
 
 
 
 
 
 
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "mask_token": {
17
  "content": "<mask>",
18
+ "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "pad_token": {
24
+ "content": "<pad>",
 
 
 
 
 
 
 
25
  "lstrip": false,
26
+ "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "unk_token": {
31
  "content": "<unk>",
32
  "lstrip": false,
33
+ "normalized": false,
34
  "rstrip": false,
35
  "single_word": false
36
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -4,7 +4,7 @@
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
@@ -12,7 +12,7 @@
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
@@ -20,7 +20,7 @@
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
@@ -28,14 +28,14 @@
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
  "4": {
37
  "content": "<mask>",
38
- "lstrip": true,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
@@ -44,19 +44,12 @@
44
  },
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
  "eos_token": "</s>",
49
- "errors": "replace",
50
  "extra_special_tokens": {},
51
  "mask_token": "<mask>",
52
- "max_length": 128,
53
  "model_max_length": 1000000000000000019884624838656,
54
- "pad_token": "</s>",
55
- "sep_token": "</s>",
56
- "stride": 0,
57
  "tokenizer_class": "GPT2Tokenizer",
58
- "trim_offsets": true,
59
- "truncation_side": "right",
60
- "truncation_strategy": "longest_first",
61
  "unk_token": "<unk>"
62
  }
 
4
  "0": {
5
  "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
 
12
  "1": {
13
  "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
 
20
  "2": {
21
  "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
 
28
  "3": {
29
  "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
  "4": {
37
  "content": "<mask>",
38
+ "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
 
44
  },
45
  "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": false,
 
47
  "eos_token": "</s>",
 
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
 
50
  "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "padding_side": "left",
 
53
  "tokenizer_class": "GPT2Tokenizer",
 
 
 
54
  "unk_token": "<unk>"
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e07f4b048e61bab16b977cf9216fdd48998c627813e56fc12bb300a3206b90
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a31d7f534f75ed0041e03bf4146f34e71d45f6fe44e0224c6606c39dc9b963
3
  size 5777
vocab.json CHANGED
The diff for this file is too large to render. See raw diff