Erica tong
commited on
Upload BertForMultilabelSequenceClassification
Browse files- config.json +90 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BertForMultilabelSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"attention_probs_dropout_prob": 0.1,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"dim": 768,
|
| 11 |
+
"dropout": 0.1,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dim": 3072,
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": [
|
| 17 |
+
{
|
| 18 |
+
"0": "sub_labels_01",
|
| 19 |
+
"1": "sub_labels_02",
|
| 20 |
+
"10": "sub_labels_11",
|
| 21 |
+
"11": "sub_labels_12",
|
| 22 |
+
"12": "sub_labels_13",
|
| 23 |
+
"13": "sub_labels_14",
|
| 24 |
+
"14": "sub_labels_15",
|
| 25 |
+
"15": "sub_labels_16",
|
| 26 |
+
"16": "sub_labels_17",
|
| 27 |
+
"17": "sub_labels_18",
|
| 28 |
+
"18": "sub_labels_19",
|
| 29 |
+
"19": "sub_labels_20",
|
| 30 |
+
"2": "sub_labels_03",
|
| 31 |
+
"20": "sub_labels_21",
|
| 32 |
+
"21": "sub_labels_22",
|
| 33 |
+
"22": "sub_labels_23",
|
| 34 |
+
"23": "sub_labels_24",
|
| 35 |
+
"3": "sub_labels_04",
|
| 36 |
+
"4": "sub_labels_05",
|
| 37 |
+
"5": "sub_labels_06",
|
| 38 |
+
"6": "sub_labels_07",
|
| 39 |
+
"7": "sub_labels_08",
|
| 40 |
+
"8": "sub_labels_09",
|
| 41 |
+
"9": "sub_labels_10"
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"initializer_range": 0.02,
|
| 45 |
+
"intermediate_size": 3072,
|
| 46 |
+
"label2id": {
|
| 47 |
+
"sub_labels_01": 0,
|
| 48 |
+
"sub_labels_02": 1,
|
| 49 |
+
"sub_labels_03": 2,
|
| 50 |
+
"sub_labels_04": 3,
|
| 51 |
+
"sub_labels_05": 4,
|
| 52 |
+
"sub_labels_06": 5,
|
| 53 |
+
"sub_labels_07": 6,
|
| 54 |
+
"sub_labels_08": 7,
|
| 55 |
+
"sub_labels_09": 8,
|
| 56 |
+
"sub_labels_10": 9,
|
| 57 |
+
"sub_labels_11": 10,
|
| 58 |
+
"sub_labels_12": 11,
|
| 59 |
+
"sub_labels_13": 12,
|
| 60 |
+
"sub_labels_14": 13,
|
| 61 |
+
"sub_labels_15": 14,
|
| 62 |
+
"sub_labels_16": 15,
|
| 63 |
+
"sub_labels_17": 16,
|
| 64 |
+
"sub_labels_18": 17,
|
| 65 |
+
"sub_labels_19": 18,
|
| 66 |
+
"sub_labels_20": 19,
|
| 67 |
+
"sub_labels_21": 20,
|
| 68 |
+
"sub_labels_22": 21,
|
| 69 |
+
"sub_labels_23": 22,
|
| 70 |
+
"sub_labels_24": 23
|
| 71 |
+
},
|
| 72 |
+
"layer_norm_eps": 1e-12,
|
| 73 |
+
"max_position_embeddings": 512,
|
| 74 |
+
"model_type": "bert",
|
| 75 |
+
"n_heads": 12,
|
| 76 |
+
"n_layers": 6,
|
| 77 |
+
"num_attention_heads": 12,
|
| 78 |
+
"num_hidden_layers": 12,
|
| 79 |
+
"pad_token_id": 0,
|
| 80 |
+
"position_embedding_type": "absolute",
|
| 81 |
+
"qa_dropout": 0.1,
|
| 82 |
+
"seq_classif_dropout": 0.2,
|
| 83 |
+
"sinusoidal_pos_embds": false,
|
| 84 |
+
"tie_weights_": true,
|
| 85 |
+
"torch_dtype": "float32",
|
| 86 |
+
"transformers_version": "4.23.1",
|
| 87 |
+
"type_vocab_size": 2,
|
| 88 |
+
"use_cache": true,
|
| 89 |
+
"vocab_size": 30522
|
| 90 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52f89bb810af8adc87b4a30f87e3d4ad7d2422c7f6802b3a4ccb2d14ea9d4373
|
| 3 |
+
size 438073773
|