Hugging Face's logo

Lekhansh
/
nuner-4k-training

PyTorch
Model card Files
xet
 Community
Lekhansh commited on
Commit
f9e2651
·
verified ·
1 Parent(s): 8a1d095

Push model using huggingface_hub.

Browse files
Files changed (8) hide show
  1. added_tokens.json +5 -0
  2. gliner_config.json +146 -0
  3. merges.txt +0 -0
  4. pytorch_model.bin +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +82 -0
  8. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<<ENT>>": 50266,
3
+ "<<SEP>>": 50267,
4
+ "[FLERT]": 50265
5
+ }
gliner_config.json ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class_token_index": 50266,
3
+ "dropout": 0.4,
4
+ "embed_ent_token": true,
5
+ "encoder_config": {
6
+ "_attn_implementation_autoset": false,
7
+ "_name_or_path": "allenai/longformer-large-4096",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "attention_mode": "longformer",
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "attention_window": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512,
35
+ 512,
36
+ 512
37
+ ],
38
+ "bad_words_ids": null,
39
+ "begin_suppress_tokens": null,
40
+ "bos_token_id": 0,
41
+ "chunk_size_feed_forward": 0,
42
+ "cross_attention_hidden_size": null,
43
+ "decoder_start_token_id": null,
44
+ "diversity_penalty": 0.0,
45
+ "do_sample": false,
46
+ "early_stopping": false,
47
+ "encoder_no_repeat_ngram_size": 0,
48
+ "eos_token_id": 2,
49
+ "exponential_decay_length_penalty": null,
50
+ "finetuning_task": null,
51
+ "forced_bos_token_id": null,
52
+ "forced_eos_token_id": null,
53
+ "gradient_checkpointing": false,
54
+ "hidden_act": "gelu",
55
+ "hidden_dropout_prob": 0.1,
56
+ "hidden_size": 1024,
57
+ "id2label": {
58
+ "0": "LABEL_0",
59
+ "1": "LABEL_1"
60
+ },
61
+ "ignore_attention_mask": false,
62
+ "initializer_range": 0.02,
63
+ "intermediate_size": 4096,
64
+ "is_decoder": false,
65
+ "is_encoder_decoder": false,
66
+ "label2id": {
67
+ "LABEL_0": 0,
68
+ "LABEL_1": 1
69
+ },
70
+ "layer_norm_eps": 1e-05,
71
+ "length_penalty": 1.0,
72
+ "max_length": 20,
73
+ "max_position_embeddings": 4098,
74
+ "min_length": 0,
75
+ "model_type": "longformer",
76
+ "no_repeat_ngram_size": 0,
77
+ "num_attention_heads": 16,
78
+ "num_beam_groups": 1,
79
+ "num_beams": 1,
80
+ "num_hidden_layers": 24,
81
+ "num_return_sequences": 1,
82
+ "onnx_export": false,
83
+ "output_attentions": false,
84
+ "output_hidden_states": false,
85
+ "output_scores": false,
86
+ "pad_token_id": 1,
87
+ "prefix": null,
88
+ "problem_type": null,
89
+ "pruned_heads": {},
90
+ "remove_invalid_values": false,
91
+ "repetition_penalty": 1.0,
92
+ "return_dict": true,
93
+ "return_dict_in_generate": false,
94
+ "sep_token_id": 2,
95
+ "suppress_tokens": null,
96
+ "task_specific_params": null,
97
+ "temperature": 1.0,
98
+ "tf_legacy_loss": false,
99
+ "tie_encoder_decoder": false,
100
+ "tie_word_embeddings": true,
101
+ "tokenizer_class": null,
102
+ "top_k": 50,
103
+ "top_p": 1.0,
104
+ "torch_dtype": null,
105
+ "torchscript": false,
106
+ "type_vocab_size": 1,
107
+ "typical_p": 1.0,
108
+ "use_bfloat16": false,
109
+ "vocab_size": 50268
110
+ },
111
+ "ent_token": "<<ENT>>",
112
+ "eval_every": 5000,
113
+ "fine_tune": true,
114
+ "fuse_layers": false,
115
+ "has_rnn": true,
116
+ "hidden_size": 768,
117
+ "labels_encoder": null,
118
+ "labels_encoder_config": null,
119
+ "log_dir": "logs",
120
+ "lr_encoder": "1e-5",
121
+ "lr_others": "5e-5",
122
+ "max_len": 2048,
123
+ "max_neg_type_ratio": 1,
124
+ "max_types": 25,
125
+ "max_width": 1,
126
+ "model_name": "allenai/longformer-large-4096",
127
+ "model_type": "gliner",
128
+ "name": "large",
129
+ "num_post_fusion_layers": 1,
130
+ "num_steps": 60000,
131
+ "post_fusion_schema": "",
132
+ "prev_path": "none",
133
+ "random_drop": true,
134
+ "root_dir": "ablation_backbone",
135
+ "sep_token": "<<SEP>>",
136
+ "shuffle_types": true,
137
+ "size_sup": -1,
138
+ "span_mode": "marker",
139
+ "subtoken_pooling": "first",
140
+ "train_batch_size": 8,
141
+ "train_data": "NuMinds_custom_data_mix.json",
142
+ "transformers_version": "4.50.0.dev0",
143
+ "vocab_size": 50268,
144
+ "warmup_ratio": 0.1,
145
+ "words_splitter_type": "whitespace"
146
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb7c1344802acd720b86c28d7a18016bcae5563fe75a949d6ec31c031662ae8
3
+ size 1798455978
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "[FLERT]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50266": {
53
+ "content": "<<ENT>>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50267": {
61
+ "content": "<<SEP>>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ }
68
+ },
69
+ "bos_token": "<s>",
70
+ "clean_up_tokenization_spaces": false,
71
+ "cls_token": "<s>",
72
+ "eos_token": "</s>",
73
+ "errors": "replace",
74
+ "extra_special_tokens": {},
75
+ "mask_token": "<mask>",
76
+ "model_max_length": 1000000000000000019884624838656,
77
+ "pad_token": "<pad>",
78
+ "sep_token": "</s>",
79
+ "tokenizer_class": "LongformerTokenizer",
80
+ "trim_offsets": true,
81
+ "unk_token": "<unk>"
82
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff