Push model using huggingface_hub.
Browse files- added_tokens.json +5 -0
- gliner_config.json +203 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +84 -0
- 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 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": -1,
|
| 3 |
+
"dropout": 0.35,
|
| 4 |
+
"embed_ent_token": true,
|
| 5 |
+
"encoder_config": {
|
| 6 |
+
"_attn_implementation_autoset": false,
|
| 7 |
+
"_name_or_path": "microsoft/deberta-large",
|
| 8 |
+
"add_cross_attention": false,
|
| 9 |
+
"architectures": null,
|
| 10 |
+
"attention_probs_dropout_prob": 0.1,
|
| 11 |
+
"bad_words_ids": null,
|
| 12 |
+
"begin_suppress_tokens": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"cross_attention_hidden_size": null,
|
| 16 |
+
"decoder_start_token_id": null,
|
| 17 |
+
"diversity_penalty": 0.0,
|
| 18 |
+
"do_sample": false,
|
| 19 |
+
"early_stopping": false,
|
| 20 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 21 |
+
"eos_token_id": null,
|
| 22 |
+
"exponential_decay_length_penalty": null,
|
| 23 |
+
"finetuning_task": null,
|
| 24 |
+
"forced_bos_token_id": null,
|
| 25 |
+
"forced_eos_token_id": null,
|
| 26 |
+
"hidden_act": "gelu",
|
| 27 |
+
"hidden_dropout_prob": 0.1,
|
| 28 |
+
"hidden_size": 1024,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1"
|
| 32 |
+
},
|
| 33 |
+
"initializer_range": 0.02,
|
| 34 |
+
"intermediate_size": 4096,
|
| 35 |
+
"is_decoder": false,
|
| 36 |
+
"is_encoder_decoder": false,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-07,
|
| 42 |
+
"legacy": true,
|
| 43 |
+
"length_penalty": 1.0,
|
| 44 |
+
"max_length": 20,
|
| 45 |
+
"max_position_embeddings": 512,
|
| 46 |
+
"max_relative_positions": -1,
|
| 47 |
+
"min_length": 0,
|
| 48 |
+
"model_type": "deberta",
|
| 49 |
+
"no_repeat_ngram_size": 0,
|
| 50 |
+
"num_attention_heads": 16,
|
| 51 |
+
"num_beam_groups": 1,
|
| 52 |
+
"num_beams": 1,
|
| 53 |
+
"num_hidden_layers": 24,
|
| 54 |
+
"num_return_sequences": 1,
|
| 55 |
+
"output_attentions": false,
|
| 56 |
+
"output_hidden_states": false,
|
| 57 |
+
"output_scores": false,
|
| 58 |
+
"pad_token_id": 0,
|
| 59 |
+
"pooler_dropout": 0,
|
| 60 |
+
"pooler_hidden_act": "gelu",
|
| 61 |
+
"pooler_hidden_size": 1024,
|
| 62 |
+
"pos_att_type": [
|
| 63 |
+
"c2p",
|
| 64 |
+
"p2c"
|
| 65 |
+
],
|
| 66 |
+
"position_biased_input": false,
|
| 67 |
+
"prefix": null,
|
| 68 |
+
"problem_type": null,
|
| 69 |
+
"pruned_heads": {},
|
| 70 |
+
"relative_attention": true,
|
| 71 |
+
"remove_invalid_values": false,
|
| 72 |
+
"repetition_penalty": 1.0,
|
| 73 |
+
"return_dict": true,
|
| 74 |
+
"return_dict_in_generate": false,
|
| 75 |
+
"sep_token_id": null,
|
| 76 |
+
"suppress_tokens": null,
|
| 77 |
+
"task_specific_params": null,
|
| 78 |
+
"temperature": 1.0,
|
| 79 |
+
"tf_legacy_loss": false,
|
| 80 |
+
"tie_encoder_decoder": false,
|
| 81 |
+
"tie_word_embeddings": true,
|
| 82 |
+
"tokenizer_class": null,
|
| 83 |
+
"top_k": 50,
|
| 84 |
+
"top_p": 1.0,
|
| 85 |
+
"torch_dtype": null,
|
| 86 |
+
"torchscript": false,
|
| 87 |
+
"type_vocab_size": 0,
|
| 88 |
+
"typical_p": 1.0,
|
| 89 |
+
"use_bfloat16": false,
|
| 90 |
+
"vocab_size": 50265
|
| 91 |
+
},
|
| 92 |
+
"ent_token": "<<ENT>>",
|
| 93 |
+
"fine_tune": false,
|
| 94 |
+
"freeze_token_rep": false,
|
| 95 |
+
"fuse_layers": false,
|
| 96 |
+
"hidden_size": 1024,
|
| 97 |
+
"labels_decoder": null,
|
| 98 |
+
"labels_encoder": "microsoft/deberta-large",
|
| 99 |
+
"labels_encoder_config": {
|
| 100 |
+
"_attn_implementation_autoset": false,
|
| 101 |
+
"_name_or_path": "microsoft/deberta-large",
|
| 102 |
+
"add_cross_attention": false,
|
| 103 |
+
"architectures": null,
|
| 104 |
+
"attention_probs_dropout_prob": 0.1,
|
| 105 |
+
"bad_words_ids": null,
|
| 106 |
+
"begin_suppress_tokens": null,
|
| 107 |
+
"bos_token_id": null,
|
| 108 |
+
"chunk_size_feed_forward": 0,
|
| 109 |
+
"cross_attention_hidden_size": null,
|
| 110 |
+
"decoder_start_token_id": null,
|
| 111 |
+
"diversity_penalty": 0.0,
|
| 112 |
+
"do_sample": false,
|
| 113 |
+
"early_stopping": false,
|
| 114 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 115 |
+
"eos_token_id": null,
|
| 116 |
+
"exponential_decay_length_penalty": null,
|
| 117 |
+
"finetuning_task": null,
|
| 118 |
+
"forced_bos_token_id": null,
|
| 119 |
+
"forced_eos_token_id": null,
|
| 120 |
+
"hidden_act": "gelu",
|
| 121 |
+
"hidden_dropout_prob": 0.1,
|
| 122 |
+
"hidden_size": 1024,
|
| 123 |
+
"id2label": {
|
| 124 |
+
"0": "LABEL_0",
|
| 125 |
+
"1": "LABEL_1"
|
| 126 |
+
},
|
| 127 |
+
"initializer_range": 0.02,
|
| 128 |
+
"intermediate_size": 4096,
|
| 129 |
+
"is_decoder": false,
|
| 130 |
+
"is_encoder_decoder": false,
|
| 131 |
+
"label2id": {
|
| 132 |
+
"LABEL_0": 0,
|
| 133 |
+
"LABEL_1": 1
|
| 134 |
+
},
|
| 135 |
+
"layer_norm_eps": 1e-07,
|
| 136 |
+
"legacy": true,
|
| 137 |
+
"length_penalty": 1.0,
|
| 138 |
+
"max_length": 20,
|
| 139 |
+
"max_position_embeddings": 512,
|
| 140 |
+
"max_relative_positions": -1,
|
| 141 |
+
"min_length": 0,
|
| 142 |
+
"model_type": "deberta",
|
| 143 |
+
"no_repeat_ngram_size": 0,
|
| 144 |
+
"num_attention_heads": 16,
|
| 145 |
+
"num_beam_groups": 1,
|
| 146 |
+
"num_beams": 1,
|
| 147 |
+
"num_hidden_layers": 24,
|
| 148 |
+
"num_return_sequences": 1,
|
| 149 |
+
"output_attentions": false,
|
| 150 |
+
"output_hidden_states": false,
|
| 151 |
+
"output_scores": false,
|
| 152 |
+
"pad_token_id": 0,
|
| 153 |
+
"pooler_dropout": 0,
|
| 154 |
+
"pooler_hidden_act": "gelu",
|
| 155 |
+
"pooler_hidden_size": 1024,
|
| 156 |
+
"pos_att_type": [
|
| 157 |
+
"c2p",
|
| 158 |
+
"p2c"
|
| 159 |
+
],
|
| 160 |
+
"position_biased_input": false,
|
| 161 |
+
"prefix": null,
|
| 162 |
+
"problem_type": null,
|
| 163 |
+
"pruned_heads": {},
|
| 164 |
+
"relative_attention": true,
|
| 165 |
+
"remove_invalid_values": false,
|
| 166 |
+
"repetition_penalty": 1.0,
|
| 167 |
+
"return_dict": true,
|
| 168 |
+
"return_dict_in_generate": false,
|
| 169 |
+
"sep_token_id": null,
|
| 170 |
+
"suppress_tokens": null,
|
| 171 |
+
"task_specific_params": null,
|
| 172 |
+
"temperature": 1.0,
|
| 173 |
+
"tf_legacy_loss": false,
|
| 174 |
+
"tie_encoder_decoder": false,
|
| 175 |
+
"tie_word_embeddings": true,
|
| 176 |
+
"tokenizer_class": null,
|
| 177 |
+
"top_k": 50,
|
| 178 |
+
"top_p": 1.0,
|
| 179 |
+
"torch_dtype": null,
|
| 180 |
+
"torchscript": false,
|
| 181 |
+
"type_vocab_size": 0,
|
| 182 |
+
"typical_p": 1.0,
|
| 183 |
+
"use_bfloat16": false,
|
| 184 |
+
"vocab_size": 50265
|
| 185 |
+
},
|
| 186 |
+
"max_len": 512,
|
| 187 |
+
"max_neg_type_ratio": 1,
|
| 188 |
+
"max_types": 25,
|
| 189 |
+
"max_width": 12,
|
| 190 |
+
"model_name": "microsoft/deberta-large",
|
| 191 |
+
"model_type": null,
|
| 192 |
+
"name": "token level bi-encoder gliner",
|
| 193 |
+
"num_post_fusion_layers": 1,
|
| 194 |
+
"num_rnn_layers": 1,
|
| 195 |
+
"post_fusion_schema": "",
|
| 196 |
+
"represent_spans": true,
|
| 197 |
+
"sep_token": "<<SEP>>",
|
| 198 |
+
"span_mode": "token_level",
|
| 199 |
+
"subtoken_pooling": "first",
|
| 200 |
+
"transformers_version": "4.48.2",
|
| 201 |
+
"vocab_size": -1,
|
| 202 |
+
"words_splitter_type": "whitespace"
|
| 203 |
+
}
|
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 sha256:79724b982f532b4fb6511ef6d8c58a99a446d1c6341446babc270a210aa566d1
|
| 3 |
+
size 3333977834
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "[SEP]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": true,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "[PAD]",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "[CLS]",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "[SEP]",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "[UNK]",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"50264": {
|
| 38 |
+
"content": "[MASK]",
|
| 39 |
+
"lstrip": true,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"50265": {
|
| 46 |
+
"content": "[FLERT]",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"50266": {
|
| 54 |
+
"content": "<<ENT>>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"50267": {
|
| 62 |
+
"content": "<<SEP>>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"bos_token": "[CLS]",
|
| 71 |
+
"clean_up_tokenization_spaces": false,
|
| 72 |
+
"cls_token": "[CLS]",
|
| 73 |
+
"do_lower_case": false,
|
| 74 |
+
"eos_token": "[SEP]",
|
| 75 |
+
"errors": "replace",
|
| 76 |
+
"extra_special_tokens": {},
|
| 77 |
+
"mask_token": "[MASK]",
|
| 78 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 79 |
+
"pad_token": "[PAD]",
|
| 80 |
+
"sep_token": "[SEP]",
|
| 81 |
+
"tokenizer_class": "DebertaTokenizer",
|
| 82 |
+
"unk_token": "[UNK]",
|
| 83 |
+
"vocab_type": "gpt2"
|
| 84 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|