kiddothe2b commited on
Commit
9d3f212
1 Parent(s): 5030688

Upload model

Browse files
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": 1,
23
+ "classifier_dropout": null,
24
+ "cls_token_id": 1,
25
+ "eos_token_id": 2,
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": 2,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.20.0",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 50000
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a755233235147981ea4148db745aba5e930be28000bd471d318f478f58ac48a
3
+ size 594155867
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "model_max_length": 4096,
7
+ "name_or_path": "lexlms/roberta-base-cased",
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "special_tokens_map_file": "data/PLMs/lex-lm-base-cased-v2/special_tokens_map.json",
11
+ "tokenizer_class": "PreTrainedTokenizerFast",
12
+ "unk_token": "<unk>"
13
+ }