Upload 7 files
Browse files- added_tokens.json +14 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +21 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"@/ChemicalEntitySrc$": 28901,
|
| 3 |
+
"@/ChemicalEntityTgt$": 28902,
|
| 4 |
+
"@/DiseaseOrPhenotypicFeatureSrc$": 28903,
|
| 5 |
+
"@/DiseaseOrPhenotypicFeatureTgt$": 28904,
|
| 6 |
+
"@/GeneOrGeneProductSrc$": 28905,
|
| 7 |
+
"@/GeneOrGeneProductTgt$": 28906,
|
| 8 |
+
"@ChemicalEntitySrc$": 28895,
|
| 9 |
+
"@ChemicalEntityTgt$": 28896,
|
| 10 |
+
"@DiseaseOrPhenotypicFeatureSrc$": 28897,
|
| 11 |
+
"@DiseaseOrPhenotypicFeatureTgt$": 28898,
|
| 12 |
+
"@GeneOrGeneProductSrc$": 28899,
|
| 13 |
+
"@GeneOrGeneProductTgt$": 28900
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_ids": 0,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-12,
|
| 16 |
+
"max_position_embeddings": 512,
|
| 17 |
+
"model_type": "bert",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 0,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.30.2",
|
| 26 |
+
"type_vocab_size": 2,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 30522
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d091951ce8c3cb963e054de3012c3b251ed5fa184d5f22b9d1eed2e48dc7e7e
|
| 3 |
+
size 1340714613
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"@ChemicalEntitySrc$",
|
| 4 |
+
"@ChemicalEntityTgt$",
|
| 5 |
+
"@DiseaseOrPhenotypicFeatureSrc$",
|
| 6 |
+
"@DiseaseOrPhenotypicFeatureTgt$",
|
| 7 |
+
"@GeneOrGeneProductSrc$",
|
| 8 |
+
"@GeneOrGeneProductTgt$",
|
| 9 |
+
"@/ChemicalEntitySrc$",
|
| 10 |
+
"@/ChemicalEntityTgt$",
|
| 11 |
+
"@/DiseaseOrPhenotypicFeatureSrc$",
|
| 12 |
+
"@/DiseaseOrPhenotypicFeatureTgt$",
|
| 13 |
+
"@/GeneOrGeneProductSrc$",
|
| 14 |
+
"@/GeneOrGeneProductTgt$"
|
| 15 |
+
],
|
| 16 |
+
"cls_token": "[CLS]",
|
| 17 |
+
"mask_token": "[MASK]",
|
| 18 |
+
"pad_token": "[PAD]",
|
| 19 |
+
"sep_token": "[SEP]",
|
| 20 |
+
"unk_token": "[UNK]"
|
| 21 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|