Hugging Face's logo

abazoge
/
DrLongformer

Fill-Mask
Transformers
PyTorch
TensorBoard
French
longformer
biomedical
medical
clinical
life science
Model card Files
xet
 Metrics Community
1
abazoge commited on
Commit
c9463e7
·
verified ·
1 Parent(s): fd7c6fa

Upload 9 files

Browse files
Files changed (9) hide show
  1. config.json +46 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. runs/1692984771.1084692/events.out.tfevents.1692984771.r6i6n0.1702000.1 +3 -0
  5. runs/events.out.tfevents.1692984771.r6i6n0.1702000.0 +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +16 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/Clinical-Longformer",
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": 0,
23
+ "classifier_dropout": null,
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "ignore_attention_mask": false,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "layer_norm_eps": 1e-05,
33
+ "max_position_embeddings": 4098,
34
+ "model_type": "longformer",
35
+ "num_attention_heads": 12,
36
+ "num_hidden_layers": 12,
37
+ "onnx_export": false,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "sep_token_id": 2,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.24.0",
43
+ "type_vocab_size": 1,
44
+ "use_cache": true,
45
+ "vocab_size": 50265
46
+ }
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 sha256:1af7d6e33348359f671c6ec3dd36c2e12afbcae188ea90136727bf139ed8a593
3
+ size 594938589
runs/1692984771.1084692/events.out.tfevents.1692984771.r6i6n0.1702000.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b2609e7220a5e90f511642e1394dd3f43beade8397a9fb8b024652649b78fe7
3
+ size 5486
runs/events.out.tfevents.1692984771.r6i6n0.1702000.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88c1b5c63020b466cef7d55b9ba8ecf4a201a5f8862c644875bb4f3fe556c107
3
+ size 19944
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 4096,
9
+ "name_or_path": "./models/Clinical-Longformer",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "LongformerTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff