ivanmorals commited on
Commit
18500c1
·
verified ·
1 Parent(s): ae64ef4

add model files

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "add_bias_logits": false,
5
+ "add_final_layer_norm": false,
6
+ "architectures": [
7
+ "BartForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "classif_dropout": 0.1,
12
+ "classifier_dropout": 0.0,
13
+ "d_model": 768,
14
+ "decoder_attention_heads": 12,
15
+ "decoder_ffn_dim": 3072,
16
+ "decoder_layerdrop": 0.0,
17
+ "decoder_layers": 6,
18
+ "decoder_start_token_id": 2,
19
+ "dropout": 0.1,
20
+ "dtype": "float32",
21
+ "encoder_attention_heads": 12,
22
+ "encoder_ffn_dim": 3072,
23
+ "encoder_layerdrop": 0.0,
24
+ "encoder_layers": 6,
25
+ "eos_token_id": 2,
26
+ "forced_eos_token_id": 2,
27
+ "gradient_checkpointing": false,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2"
32
+ },
33
+ "init_std": 0.02,
34
+ "is_decoder": false,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "normalize_before": false,
44
+ "normalize_embedding": true,
45
+ "pad_token_id": 1,
46
+ "scale_embedding": false,
47
+ "task_specific_params": {
48
+ "summarization": {
49
+ "length_penalty": 1.0,
50
+ "max_length": 128,
51
+ "min_length": 12,
52
+ "num_beams": 4
53
+ },
54
+ "summarization_cnn": {
55
+ "length_penalty": 2.0,
56
+ "max_length": 142,
57
+ "min_length": 56,
58
+ "num_beams": 4
59
+ },
60
+ "summarization_xsum": {
61
+ "length_penalty": 1.0,
62
+ "max_length": 62,
63
+ "min_length": 11,
64
+ "num_beams": 6
65
+ }
66
+ },
67
+ "tie_word_embeddings": true,
68
+ "transformers_version": "5.5.0",
69
+ "use_cache": false,
70
+ "vocab_size": 50265
71
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": [
7
+ 2
8
+ ],
9
+ "forced_bos_token_id": 0,
10
+ "forced_eos_token_id": 2,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 4,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "5.5.0",
15
+ "use_cache": true
16
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9dc9ffae85920773b2b5774f37b9630b197fc455008db011e6288a451870cb8
3
+ size 557912620
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "is_local": false,
9
+ "mask_token": "<mask>",
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edab2539a81b65c2a76c4c39bed219aa02358f44f3286429f83165442a1b53fa
3
+ size 5329