Hugging Face's logo

dvssr
/
unipelt

Text2Text Generation
Transformers
TensorBoard
Safetensors
bart
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
unipelt
File size: 3,942 Bytes 
e86b626
 
 
 
 
 
4ffef8b
e86b626
 
4ffef8b
58c2cb8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ffef8b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58c2cb8
 
e86b626
 
 
5abd34e
e86b626
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
 
{
  "_name_or_path": "mse30/bart-base-finetuned-pubmed",
  "activation_dropout": 0.1,
  "activation_function": "gelu",
  "adapters": {
    "adapters": {
      "unipelt": "0815dd75d5ff5808"
    },
    "config_map": {
      "0815dd75d5ff5808": {
        "architecture": "union",
        "configs": [
          {
            "alpha": 8,
            "architecture": "lora",
            "attn_matrices": [
              "q",
              "v"
            ],
            "composition_mode": "add",
            "dropout": 0.0,
            "init_weights": "lora",
            "intermediate_lora": false,
            "leave_out": [],
            "output_lora": false,
            "r": 8,
            "selfattn_lora": true,
            "use_gating": true
          },
          {
            "architecture": "prefix_tuning",
            "bottleneck_size": 512,
            "cross_prefix": true,
            "dropout": 0.0,
            "encoder_prefix": true,
            "flat": false,
            "leave_out": [],
            "non_linearity": "tanh",
            "prefix_length": 10,
            "shared_gating": true,
            "use_gating": true
          },
          {
            "adapter_residual_before_ln": false,
            "cross_adapter": false,
            "factorized_phm_W": true,
            "factorized_phm_rule": false,
            "hypercomplex_nonlinearity": "glorot-uniform",
            "init_weights": "bert",
            "inv_adapter": null,
            "inv_adapter_reduction_factor": null,
            "is_parallel": false,
            "learn_phm": true,
            "leave_out": [],
            "ln_after": false,
            "ln_before": false,
            "mh_adapter": false,
            "non_linearity": "relu",
            "original_ln_after": true,
            "original_ln_before": true,
            "output_adapter": true,
            "phm_bias": true,
            "phm_c_init": "normal",
            "phm_dim": 4,
            "phm_init_range": 0.0001,
            "phm_layer": false,
            "phm_rank": 1,
            "reduction_factor": 16,
            "residual_before_ln": true,
            "scaling": 1.0,
            "shared_W_phm": false,
            "shared_phm_rule": true,
            "use_gating": true
          }
        ]
      }
    },
    "fusion_config_map": {},
    "fusions": {}
  },
  "add_bias_logits": false,
  "add_final_layer_norm": false,
  "architectures": [
    "BartForConditionalGeneration"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 0,
  "classif_dropout": 0.1,
  "classifier_dropout": 0.0,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": true,
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "eos_token_id": 2,
  "forced_eos_token_id": 2,
  "gradient_checkpointing": false,
  "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
  },
  "max_position_embeddings": 1024,
  "model_type": "bart",
  "no_repeat_ngram_size": 3,
  "normalize_before": false,
  "normalize_embedding": true,
  "num_beams": 4,
  "num_hidden_layers": 6,
  "pad_token_id": 1,
  "scale_embedding": false,
  "task_specific_params": {
    "summarization": {
      "length_penalty": 1.0,
      "max_length": 128,
      "min_length": 12,
      "num_beams": 4
    },
    "summarization_cnn": {
      "length_penalty": 2.0,
      "max_length": 142,
      "min_length": 56,
      "num_beams": 4
    },
    "summarization_xsum": {
      "length_penalty": 1.0,
      "max_length": 62,
      "min_length": 11,
      "num_beams": 6
    }
  },
  "torch_dtype": "float32",
  "transformers_version": "4.36.2",
  "use_cache": true,
  "vocab_size": 50265
}