Hugging Face's logo

knowledgator
/
gliner-multitask-large-v0.5

Token Classification
GLiNER
PyTorch
English
NER
information extraction
relation extraction
summarization
sentiment extraction
question-answering
Model card Files Community
8
gliner-multitask-large-v0.5
File size: 3,756 Bytes 
87e2b84
2e17664
87e2b84
2e17664
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f40557b
2e17664
 
 
 
 
 
 
 
87e2b84
f40557b
87e2b84
f40557b
 
2e17664
 
 
 
 
 
 
 
 
 
f40557b
2e17664
 
f40557b
2e17664
 
87e2b84
2e17664
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "class_token_index": 128002,
  "dropout": 0.1,
  "embed_ent_token": true,
  "encoder_config": {
    "_attn_implementation_autoset": false,
    "_name_or_path": "microsoft/deberta-v3-large",
    "add_cross_attention": false,
    "architectures": null,
    "attention_probs_dropout_prob": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-07,
    "legacy": true,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 512,
    "max_relative_positions": -1,
    "min_length": 0,
    "model_type": "deberta-v2",
    "no_repeat_ngram_size": 0,
    "norm_rel_ebd": "layer_norm",
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 0,
    "pooler_dropout": 0,
    "pooler_hidden_act": "gelu",
    "pooler_hidden_size": 1024,
    "pos_att_type": [
      "p2c",
      "c2p"
    ],
    "position_biased_input": false,
    "position_buckets": 256,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "relative_attention": true,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "share_att_key": true,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "type_vocab_size": 0,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vocab_size": 128004
  },
  "ent_token": "<<ENT>>",
  "eval_every": 1000,
  "fine_tune": true,
  "freeze_token_rep": false,
  "fuse_layers": false,
  "has_rnn": true,
  "hidden_size": 512,
  "labels_encoder": null,
  "labels_encoder_config": null,
  "log_dir": "logs_final",
  "loss_alpha": 0.75,
  "loss_gamma": 0,
  "loss_reduction": "sum",
  "lr_encoder": "5e-6",
  "lr_others": "7e-6",
  "max_len": 768,
  "max_neg_type_ratio": 1,
  "max_types": 30,
  "max_width": 100,
  "model_name": "microsoft/deberta-v3-large",
  "model_type": "gliner",
  "name": "token level gliner large",
  "num_post_fusion_layers": 1,
  "num_steps": 6000,
  "post_fusion_schema": "",
  "prev_path": "logs_large/model_120000",
  "random_drop": true,
  "root_dir": "gliner_logs",
  "save_total_limit": 10,
  "scheduler_type": "linear",
  "sep_token": "<<SEP>>",
  "shuffle_types": true,
  "size_sup": -1,
  "span_mode": "token_level",
  "subtoken_pooling": "first",
  "train_batch_size": 8,
  "train_data": "../../data/unie_ner1.json",
  "transformers_version": "4.47.1",
  "val_data_dir": "none",
  "vocab_size": 128004,
  "warmup_ratio": 0.1,
  "weight_decay_encoder": 0.01,
  "weight_decay_other": 0.01,
  "words_splitter_type": "whitespace"
}