vitvit commited on
Commit
a5156f0
1 Parent(s): 6eec6fd

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/vitalysh/Projects/HeLM/resources/Longformer/longformer-he/checkpoint-342400",
3
+ "architectures": [
4
+ "LongformerForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "classifier_dropout": null,
23
+ "eos_token_id": 2,
24
+ "hidden_act": "gelu",
25
+ "hidden_dropout_prob": 0.1,
26
+ "hidden_size": 768,
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 4098,
31
+ "model_type": "longformer",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "onnx_export": false,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "sep_token_id": 2,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.24.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 50265
43
+ }
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 sha256:0479301d5a26adc50901335a2139018f2f5958d791ab53058424d4bc879098d5
3
+ size 594937821
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": {
8
+ "__type": "AddedToken",
9
+ "content": "<mask>",
10
+ "lstrip": true,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "model_max_length": 4096,
16
+ "name_or_path": "/home/vitalysh/Projects/HeLM/resources/Longformer/longformer-he",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "special_tokens_map_file": null,
20
+ "tokenizer_class": "LongformerTokenizer",
21
+ "trim_offsets": true,
22
+ "unk_token": "<unk>"
23
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff