Hugging Face's logo

realsanjeev
/
results

Text Generation
Transformers
Safetensors
Nepali
bart
text2text-generation
Generated from Trainer
Model card Files
xet
 Community
3
Sanjeev Bhandari commited on
Commit
31023e0
·
verified ·
1 Parent(s): a53a020

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. config.json +50 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +51 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +80 -0
  7. training_args.bin +3 -0
  8. unigram.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 55000,
3
+ "<s>": 55001
4
+ }
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sanjeev-bhandari01/nepali-text-summerization",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "BartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 768,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 768,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 1,
17
+ "do_sample": true,
18
+ "dropout": 0.1,
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 768,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 6,
23
+ "eos_token_id": 1,
24
+ "forced_eos_token_id": 1,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1",
28
+ "2": "LABEL_2"
29
+ },
30
+ "init_std": 0.02,
31
+ "is_encoder_decoder": true,
32
+ "label2id": {
33
+ "LABEL_0": 0,
34
+ "LABEL_1": 1,
35
+ "LABEL_2": 2
36
+ },
37
+ "length_penalty": 2.0,
38
+ "max_length": 128,
39
+ "max_position_embeddings": 1000,
40
+ "min_length": 32,
41
+ "model_type": "bart",
42
+ "num_beams": 4,
43
+ "num_hidden_layers": 6,
44
+ "pad_token_id": 3,
45
+ "scale_embedding": false,
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.35.2",
48
+ "use_cache": true,
49
+ "vocab_size": 55000
50
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e612e9c620d09618dc1f3451c4a019534d004cb625536660ac9c962e17e4831
3
+ size 402350000
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<cls>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<sep>",
18
+ "lstrip": false,
19
+ "normalized": false,
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": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<cls>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<sep>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "55000": {
45
+ "content": "</s>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "55001": {
53
+ "content": "<s>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "bos_token": "<cls>",
62
+ "clean_up_tokenization_spaces": true,
63
+ "cls_token": "<s>",
64
+ "eos_token": "<sep>",
65
+ "errors": "replace",
66
+ "mask_token": "<mask>",
67
+ "max_length": 1000,
68
+ "model_max_length": 1000,
69
+ "pad_to_multiple_of": null,
70
+ "pad_token": "<pad>",
71
+ "pad_token_type_id": 0,
72
+ "padding_side": "right",
73
+ "sep_token": "</s>",
74
+ "stride": 0,
75
+ "tokenizer_class": "BartTokenizer",
76
+ "trim_offsets": true,
77
+ "truncation_side": "right",
78
+ "truncation_strategy": "longest_first",
79
+ "unk_token": "<unk>"
80
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e3590036515e42deb93fa456c7e33d0b0dc7e3b50de1abe79bb66b7a80c182b
3
+ size 4664
unigram.json ADDED
The diff for this file is too large to render. See raw diff