Hugging Face's logo

dlicari
/
lsg8k-mbart-summarization-mlsum

Text2Text Generation
Transformers
PyTorch
mbart
custom_code
Model card Files Community
lsg8k-mbart-summarization-mlsum
File size: 2,203 Bytes 
bdf4ad3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
{
  "_name_or_path": "ARTeLab/mbart-summarization-mlsum",
  "_num_labels": 3,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "adaptive": true,
  "add_bias_logits": false,
  "add_final_layer_norm": true,
  "architectures": [
    "LSGMBartForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "modeling_lsg_mbart.LSGMBartConfig",
    "AutoModel": "modeling_lsg_mbart.LSGMBartModel",
    "AutoModelForCausalLM": "modeling_lsg_mbart.LSGMBartForCausalLM",
    "AutoModelForQuestionAnswering": "modeling_lsg_mbart.LSGMBartForQuestionAnswering",
    "AutoModelForSeq2SeqLM": "modeling_lsg_mbart.LSGMBartForConditionalGeneration",
    "AutoModelForSequenceClassification": "modeling_lsg_mbart.LSGMBartForSequenceClassification"
  },
  "base_model_prefix": "lsg",
  "block_size": 128,
  "bos_token_id": 0,
  "classif_dropout": 0.0,
  "classifier_dropout": 0.0,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 250011,
  "dropout": 0.1,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2
  },
  "lsh_num_pre_rounds": 1,
  "mask_first_token": false,
  "max_length": 1024,
  "max_position_embeddings": 8192,
  "model_type": "mbart",
  "normalize_before": true,
  "normalize_embedding": true,
  "num_beams": 5,
  "num_global_tokens": 14,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "pass_global_tokens_to_decoder": true,
  "pool_with_global": true,
  "scale_embedding": true,
  "sparse_block_size": 128,
  "sparsity_factor": 2,
  "sparsity_type": "norm",
  "static_position_embeddings": false,
  "task_specific_params": {
    "translation_en_to_ro": {
      "decoder_start_token_id": 250020
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.25.1",
  "use_cache": true,
  "vocab_size": 250027
}