Hugging Face's logo

ssdatar
/
output

Text2Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ssdatar commited on
Commit
f2e3399
•
1 Parent(s): b9794ef

Training in progress, step 13000

Browse files
Files changed (6) hide show
  1. config.json +68 -23
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +13 -5
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +12 -10
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,31 +1,76 @@
1
  {
2
- "_name_or_path": "google/electra-large-generator",
 
 
 
 
3
  "architectures": [
4
- "ElectraForCausalLM"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "embedding_size": 1024,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 256,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 1024,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  "is_decoder": true,
15
- "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 512,
17
- "model_type": "electra",
18
- "num_attention_heads": 4,
19
- "num_hidden_layers": 24,
20
- "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "summary_activation": "gelu",
23
- "summary_last_dropout": 0.1,
24
- "summary_type": "first",
25
- "summary_use_proj": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  "torch_dtype": "float32",
27
  "transformers_version": "4.33.3",
28
- "type_vocab_size": 2,
29
  "use_cache": true,
30
- "vocab_size": 30522
31
  }
 
1
  {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
  "architectures": [
8
+ "BartForCausalLM"
9
  ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
  "is_decoder": true,
37
+ "is_encoder_decoder": false,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "bart",
45
+ "no_repeat_ngram_size": 3,
46
+ "normalize_before": false,
47
+ "normalize_embedding": true,
48
+ "num_beams": 4,
49
+ "num_hidden_layers": 6,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": false,
52
+ "task_specific_params": {
53
+ "summarization": {
54
+ "length_penalty": 1.0,
55
+ "max_length": 128,
56
+ "min_length": 12,
57
+ "num_beams": 4
58
+ },
59
+ "summarization_cnn": {
60
+ "length_penalty": 2.0,
61
+ "max_length": 142,
62
+ "min_length": 56,
63
+ "num_beams": 4
64
+ },
65
+ "summarization_xsum": {
66
+ "length_penalty": 1.0,
67
+ "max_length": 62,
68
+ "min_length": 11,
69
+ "num_beams": 6
70
+ }
71
+ },
72
  "torch_dtype": "float32",
73
  "transformers_version": "4.33.3",
 
74
  "use_cache": true,
75
+ "vocab_size": 50265
76
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7069abb1970db1b61ba8437a477a4ae9e0733f5263c096f257f74754b4863452
3
- size 205317885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40764ce2efc107b6471df7c981e46083c1a6dcf615acecc6b036d7e57f7361d7
3
+ size 384469069
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fc687b11de0bc1b3d8348f92e3b49ef1089a621506c7661fbf3248fcd54947e
3
- size 711649
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bb7ca1064b9430bf0dbda9cb011b3be3449663b1f7f2abd9c089c700cd4a83
3
+ size 2108872
tokenizer_config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
6
- "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "ElectraTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
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
+ "model_max_length": 1024,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "BartTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e20146335638a737527b74cf88ca20db045bd09d3bd01f62c804d1edc5fa00b
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fed6a14f77dbaa02c7ee5e4897e67646fd134c8e793e583f4c9e2b0330790378
3
  size 4027