dantepalacio commited on
Commit
05f2367
1 Parent(s): 5466dc3

Upload MBartForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +60 -0
  2. generation_config.json +13 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/model-ru-mbart-2595",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
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_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "length_penalty": 0.6,
43
+ "max_length": 256,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "no_repeat_ngram_size": 2,
47
+ "normalize_before": true,
48
+ "normalize_embedding": true,
49
+ "num_beams": 10,
50
+ "num_hidden_layers": 12,
51
+ "output_past": true,
52
+ "pad_token_id": 1,
53
+ "scale_embedding": true,
54
+ "static_position_embeddings": false,
55
+ "tokenizer_class": "MBart50Tokenizer",
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.31.0",
58
+ "use_cache": true,
59
+ "vocab_size": 24261
60
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "forced_eos_token_id": 2,
7
+ "length_penalty": 0.6,
8
+ "max_length": 256,
9
+ "no_repeat_ngram_size": 2,
10
+ "num_beams": 10,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.31.0"
13
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd162dee051c1a32db2340aab7f8712ede2ceb80c00e507aea0db2d86ea891a
3
+ size 1518935453