riho1710 commited on
Commit
365a1df
1 Parent(s): 999c0d8

Upload MBartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +77 -0
  2. generation_config.json +12 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "riho1710/RMModel-30t15w3s6p-cut-brackets-512-a100-newsave",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
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
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "no_repeat_ngram_size": 3,
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 4,
49
+ "num_hidden_layers": 6,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": false,
52
+ "static_position_embeddings": false,
53
+ "task_specific_params": {
54
+ "summarization": {
55
+ "length_penalty": 1.0,
56
+ "max_length": 128,
57
+ "min_length": 12,
58
+ "num_beams": 4
59
+ },
60
+ "summarization_cnn": {
61
+ "length_penalty": 2.0,
62
+ "max_length": 142,
63
+ "min_length": 56,
64
+ "num_beams": 4
65
+ },
66
+ "summarization_xsum": {
67
+ "length_penalty": 1.0,
68
+ "max_length": 62,
69
+ "min_length": 11,
70
+ "num_beams": 6
71
+ }
72
+ },
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.32.1",
75
+ "use_cache": true,
76
+ "vocab_size": 32002
77
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.32.1"
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d44fe0be10532cb3dda67b5e4f02af09787c7328d79198721c0079c28e98c0
3
+ size 501808298