Commit
•
d8ab398
1
Parent(s):
9aaa997
Upload model
Browse files- config.json +47 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongformerForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
+
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512
|
| 21 |
+
],
|
| 22 |
+
"bos_token_id": null,
|
| 23 |
+
"classifier_dropout": null,
|
| 24 |
+
"cls_token_id": 2,
|
| 25 |
+
"eos_token_id": null,
|
| 26 |
+
"gradient_checkpointing": false,
|
| 27 |
+
"hidden_act": "gelu",
|
| 28 |
+
"hidden_dropout_prob": 0.1,
|
| 29 |
+
"hidden_size": 768,
|
| 30 |
+
"ignore_attention_mask": false,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 3072,
|
| 33 |
+
"layer_norm_eps": 1e-05,
|
| 34 |
+
"max_position_embeddings": 4098,
|
| 35 |
+
"model_max_length": 4096,
|
| 36 |
+
"model_type": "longformer",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_hidden_layers": 12,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"position_embedding_type": "absolute",
|
| 41 |
+
"sep_token_id": 3,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.20.0",
|
| 44 |
+
"type_vocab_size": 2,
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"vocab_size": 30522
|
| 47 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5704f72fe196178b8e605d44a5d482473482716eafdcb168f0c2749391335031
|
| 3 |
+
size 534363737
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 4096,
|
| 7 |
+
"name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|