Upload gliner_config.json
Browse files- gliner_config.json +88 -0
gliner_config.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"class_token_index": 128002,
|
| 3 |
+
"dropout": 0.4,
|
| 4 |
+
"embed_ent_token": true,
|
| 5 |
+
"encoder_config": {
|
| 6 |
+
"_name_or_path": "microsoft/deberta-v3-small",
|
| 7 |
+
"architectures": null,
|
| 8 |
+
"attention_probs_dropout_prob": 0.1,
|
| 9 |
+
"bos_token_id": null,
|
| 10 |
+
"chunk_size_feed_forward": 0,
|
| 11 |
+
"dtype": null,
|
| 12 |
+
"eos_token_id": null,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "LABEL_0",
|
| 18 |
+
"1": "LABEL_1"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"is_encoder_decoder": false,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"LABEL_0": 0,
|
| 25 |
+
"LABEL_1": 1
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-07,
|
| 28 |
+
"legacy": true,
|
| 29 |
+
"max_position_embeddings": 512,
|
| 30 |
+
"max_relative_positions": -1,
|
| 31 |
+
"model_type": "deberta-v2",
|
| 32 |
+
"norm_rel_ebd": "layer_norm",
|
| 33 |
+
"num_attention_heads": 12,
|
| 34 |
+
"num_hidden_layers": 6,
|
| 35 |
+
"output_attentions": false,
|
| 36 |
+
"output_hidden_states": false,
|
| 37 |
+
"pad_token_id": 0,
|
| 38 |
+
"pooler_dropout": 0,
|
| 39 |
+
"pooler_hidden_act": "gelu",
|
| 40 |
+
"pooler_hidden_size": 768,
|
| 41 |
+
"pos_att_type": [
|
| 42 |
+
"p2c",
|
| 43 |
+
"c2p"
|
| 44 |
+
],
|
| 45 |
+
"position_biased_input": false,
|
| 46 |
+
"position_buckets": 256,
|
| 47 |
+
"problem_type": null,
|
| 48 |
+
"relative_attention": true,
|
| 49 |
+
"return_dict": true,
|
| 50 |
+
"share_att_key": true,
|
| 51 |
+
"tie_word_embeddings": true,
|
| 52 |
+
"type_vocab_size": 0,
|
| 53 |
+
"vocab_size": 128004
|
| 54 |
+
},
|
| 55 |
+
"ent_token": "<<ENT>>",
|
| 56 |
+
"eval_every": 5000,
|
| 57 |
+
"fine_tune": true,
|
| 58 |
+
"fuse_layers": false,
|
| 59 |
+
"hidden_size": 512,
|
| 60 |
+
"lr_encoder": "1e-5",
|
| 61 |
+
"lr_others": "5e-5",
|
| 62 |
+
"max_len": 384,
|
| 63 |
+
"max_neg_type_ratio": 1,
|
| 64 |
+
"max_types": 25,
|
| 65 |
+
"max_width": 12,
|
| 66 |
+
"model_name": "microsoft/deberta-v3-small",
|
| 67 |
+
"model_type": null,
|
| 68 |
+
"name": "correct",
|
| 69 |
+
"neg_spans_ratio": 1.0,
|
| 70 |
+
"num_post_fusion_layers": 1,
|
| 71 |
+
"num_rnn_layers": 1,
|
| 72 |
+
"num_steps": 30000,
|
| 73 |
+
"post_fusion_schema": "",
|
| 74 |
+
"random_drop": true,
|
| 75 |
+
"represent_spans": false,
|
| 76 |
+
"sep_token": "<<SEP>>",
|
| 77 |
+
"shuffle_types": true,
|
| 78 |
+
"size_sup": -1,
|
| 79 |
+
"span_loss_coef": 1.0,
|
| 80 |
+
"span_mode": "markerV0",
|
| 81 |
+
"subtoken_pooling": "first",
|
| 82 |
+
"token_loss_coef": 1.0,
|
| 83 |
+
"train_batch_size": 8,
|
| 84 |
+
"transformers_version": "5.1.0",
|
| 85 |
+
"vocab_size": 128004,
|
| 86 |
+
"warmup_ratio": 3000,
|
| 87 |
+
"words_splitter_type": "whitespace"
|
| 88 |
+
}
|