rafmacalaba commited on
Commit
e6c6163
·
verified ·
1 Parent(s): 2241dba

Push model using huggingface_hub.

Browse files
gliner_config.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "class_token_index": 128002,
4
+ "dropout": 0.4,
5
+ "embed_ent_token": true,
6
+ "encoder_config": {
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
+ "architectures": null,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bos_token_id": null,
11
+ "chunk_size_feed_forward": 0,
12
+ "dtype": null,
13
+ "eos_token_id": null,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 1024,
17
+ "id2label": {
18
+ "0": "LABEL_0",
19
+ "1": "LABEL_1"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 4096,
23
+ "is_encoder_decoder": false,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1
27
+ },
28
+ "layer_norm_eps": 1e-07,
29
+ "legacy": true,
30
+ "max_position_embeddings": 512,
31
+ "max_relative_positions": -1,
32
+ "model_type": "deberta-v2",
33
+ "norm_rel_ebd": "layer_norm",
34
+ "num_attention_heads": 16,
35
+ "num_hidden_layers": 24,
36
+ "output_attentions": false,
37
+ "output_hidden_states": false,
38
+ "pad_token_id": 0,
39
+ "pooler_dropout": 0.0,
40
+ "pooler_hidden_act": "gelu",
41
+ "pooler_hidden_size": 1024,
42
+ "pos_att_type": [
43
+ "p2c",
44
+ "c2p"
45
+ ],
46
+ "position_biased_input": false,
47
+ "position_buckets": 256,
48
+ "problem_type": null,
49
+ "relative_attention": true,
50
+ "return_dict": true,
51
+ "share_att_key": true,
52
+ "tie_word_embeddings": true,
53
+ "type_vocab_size": 0,
54
+ "vocab_size": 128004
55
+ },
56
+ "ent_token": "<<ENT>>",
57
+ "eos_token_id": 2,
58
+ "eval_every": 5000,
59
+ "fine_tune": true,
60
+ "fuse_layers": false,
61
+ "hidden_size": 512,
62
+ "id_to_classes": null,
63
+ "lr_encoder": "1e-5",
64
+ "lr_others": "5e-5",
65
+ "max_len": 384,
66
+ "max_neg_type_ratio": 1,
67
+ "max_types": 25,
68
+ "max_width": 12,
69
+ "model_name": "microsoft/deberta-v3-large",
70
+ "model_type": null,
71
+ "name": "correct",
72
+ "neg_spans_ratio": 1.0,
73
+ "num_post_fusion_layers": 1,
74
+ "num_rnn_layers": 1,
75
+ "num_steps": 30000,
76
+ "pad_token_id": 0,
77
+ "post_fusion_schema": "",
78
+ "precomputed_prompts_mode": null,
79
+ "random_drop": true,
80
+ "represent_spans": false,
81
+ "sep_token": "<<SEP>>",
82
+ "shuffle_types": true,
83
+ "size_sup": -1,
84
+ "span_encoder_config": null,
85
+ "span_loss_coef": 1.0,
86
+ "span_mode": "markerV0",
87
+ "subtoken_pooling": "first",
88
+ "token_loss_coef": 1.0,
89
+ "train_batch_size": 8,
90
+ "transformers_version": "5.13.1",
91
+ "use_cache": false,
92
+ "vocab_size": 128004,
93
+ "warmup_ratio": 3000,
94
+ "words_splitter_type": "whitespace"
95
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e728cdaf7f913c45f92f67c9d039eff17d95a94f718f02d617e57facba32894c
3
+ size 1782006819
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "backend": "tokenizers",
4
+ "bos_token": "[CLS]",
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": false,
7
+ "eos_token": "[SEP]",
8
+ "extra_special_tokens": [
9
+ "[PAD]",
10
+ "[CLS]",
11
+ "[SEP]"
12
+ ],
13
+ "is_local": false,
14
+ "local_files_only": false,
15
+ "mask_token": "[MASK]",
16
+ "model_max_length": 1000000000000000019884624838656,
17
+ "pad_token": "[PAD]",
18
+ "sep_token": "[SEP]",
19
+ "split_by_punct": false,
20
+ "tokenizer_class": "DebertaV2Tokenizer",
21
+ "unk_id": 3,
22
+ "unk_token": "[UNK]",
23
+ "vocab_type": "spm"
24
+ }