Hugging Face's logo

SushantGautam
/
SoccerSum-NarSum

Text2Text Generation
Transformers
PyTorch
English
led
Generated from Trainer
Inference Endpoints
Model card Files Community
SushantGautam commited on
Commit
78c5bb6
•
1 Parent(s): 2a11fe4

Training in progress, step 500

Browse files
Files changed (6) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +49 -61
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +55 -67
  6. training_args.bin +1 -1
config.json CHANGED
@@ -52,5 +52,5 @@
52
  "torch_dtype": "float32",
53
  "transformers_version": "4.21.0.dev0",
54
  "use_cache": true,
55
- "vocab_size": 250054
56
  }
 
52
  "torch_dtype": "float32",
53
  "transformers_version": "4.21.0.dev0",
54
  "use_cache": true,
55
+ "vocab_size": 50265
56
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a12cf3ae7ea175bb9fee67caee16b6e8f5707e928f1c850a0a280b76f51026d
3
- size 1262229553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71ea35dfcb0b6c2c4871722e2fbd2b82794b48c6d23e6faf0c0f447800927858
3
+ size 647678513
special_tokens_map.json CHANGED
@@ -1,63 +1,51 @@
1
  {
2
- "additional_special_tokens": [
3
- "ar_AR",
4
- "cs_CZ",
5
- "de_DE",
6
- "en_XX",
7
- "es_XX",
8
- "et_EE",
9
- "fi_FI",
10
- "fr_XX",
11
- "gu_IN",
12
- "hi_IN",
13
- "it_IT",
14
- "ja_XX",
15
- "kk_KZ",
16
- "ko_KR",
17
- "lt_LT",
18
- "lv_LV",
19
- "my_MM",
20
- "ne_NP",
21
- "nl_XX",
22
- "ro_RO",
23
- "ru_RU",
24
- "si_LK",
25
- "tr_TR",
26
- "vi_VN",
27
- "zh_CN",
28
- "af_ZA",
29
- "az_AZ",
30
- "bn_IN",
31
- "fa_IR",
32
- "he_IL",
33
- "hr_HR",
34
- "id_ID",
35
- "ka_GE",
36
- "km_KH",
37
- "mk_MK",
38
- "ml_IN",
39
- "mn_MN",
40
- "mr_IN",
41
- "pl_PL",
42
- "ps_AF",
43
- "pt_XX",
44
- "sv_SE",
45
- "sw_KE",
46
- "ta_IN",
47
- "te_IN",
48
- "th_TH",
49
- "tl_XX",
50
- "uk_UA",
51
- "ur_PK",
52
- "xh_ZA",
53
- "gl_ES",
54
- "sl_SI"
55
- ],
56
- "bos_token": "<s>",
57
- "cls_token": "<s>",
58
- "eos_token": "</s>",
59
- "mask_token": "<mask>",
60
- "pad_token": "<pad>",
61
- "sep_token": "</s>",
62
- "unk_token": "<unk>"
63
  }
 
1
  {
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": 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": "</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
+ }
 
 
 
 
 
 
 
 
 
 
 
 
51
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81d3bd2b77106f20bec312f7c2fc840c836355c4ad0a937d6fdcdb92b7577cfe
3
- size 17109832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7429bd0a6bae8c971623be70159e055d55cbbcd9b54c6fd225b3141300daf5ff
3
+ size 2108685
tokenizer_config.json CHANGED
@@ -1,61 +1,30 @@
1
  {
2
- "additional_special_tokens": [
3
- "ar_AR",
4
- "cs_CZ",
5
- "de_DE",
6
- "en_XX",
7
- "es_XX",
8
- "et_EE",
9
- "fi_FI",
10
- "fr_XX",
11
- "gu_IN",
12
- "hi_IN",
13
- "it_IT",
14
- "ja_XX",
15
- "kk_KZ",
16
- "ko_KR",
17
- "lt_LT",
18
- "lv_LV",
19
- "my_MM",
20
- "ne_NP",
21
- "nl_XX",
22
- "ro_RO",
23
- "ru_RU",
24
- "si_LK",
25
- "tr_TR",
26
- "vi_VN",
27
- "zh_CN",
28
- "af_ZA",
29
- "az_AZ",
30
- "bn_IN",
31
- "fa_IR",
32
- "he_IL",
33
- "hr_HR",
34
- "id_ID",
35
- "ka_GE",
36
- "km_KH",
37
- "mk_MK",
38
- "ml_IN",
39
- "mn_MN",
40
- "mr_IN",
41
- "pl_PL",
42
- "ps_AF",
43
- "pt_XX",
44
- "sv_SE",
45
- "sw_KE",
46
- "ta_IN",
47
- "te_IN",
48
- "th_TH",
49
- "tl_XX",
50
- "uk_UA",
51
- "ur_PK",
52
- "xh_ZA",
53
- "gl_ES",
54
- "sl_SI"
55
- ],
56
- "bos_token": "<s>",
57
- "cls_token": "<s>",
58
- "eos_token": "</s>",
59
  "mask_token": {
60
  "__type": "AddedToken",
61
  "content": "<mask>",
@@ -64,14 +33,33 @@
64
  "rstrip": false,
65
  "single_word": false
66
  },
67
- "model_max_length": 1024,
68
- "name_or_path": "facebook/mbart-large-50",
69
- "pad_token": "<pad>",
70
- "sep_token": "</s>",
71
- "sp_model_kwargs": {},
72
- "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json",
73
- "src_lang": null,
74
- "tgt_lang": null,
75
- "tokenizer_class": "MBart50Tokenizer",
76
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "mask_token": {
29
  "__type": "AddedToken",
30
  "content": "<mask>",
 
33
  "rstrip": false,
34
  "single_word": false
35
  },
36
+ "model_max_length": 16384,
37
+ "name_or_path": "allenai/led-base-16384-ms2",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/home/johnmg/.cache/huggingface/transformers/05da652a7fca41c1c18027c1201e473217bb373e370d1283e3de49d5880cbf0c.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0",
55
+ "tokenizer_class": "LEDTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a163c7f7bf6a54396c84cd4745fc85fb6a5fbbc37459350f76c4b8e9242aff75
3
  size 3567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5786cbdc245faadf1d073d31617c9677fbae44a341ec26e9ad516a5f3824205d
3
  size 3567