tanikina commited on
Commit
bf1ba7e
1 Parent(s): b32bc67

upload the model (resized tokenizer)

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<|par|>": 50274, "</|title|>": 50272, "</|sec|>": 50266, "<|sec-title|>": 50267, "<|sent|>": 50273, "<|title|>": 50271, "<|abs|>": 50269, "<|sec|>": 50265, "</|sec-title|>": 50268, "</|abs|>": 50270}
config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/longformer-large-4096",
3
+ "architectures": [
4
+ "LongformerModel"
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
+ 512,
22
+ 512,
23
+ 512,
24
+ 512,
25
+ 512,
26
+ 512,
27
+ 512,
28
+ 512,
29
+ 512,
30
+ 512,
31
+ 512,
32
+ 512
33
+ ],
34
+ "bos_token_id": 0,
35
+ "eos_token_id": 2,
36
+ "gradient_checkpointing": false,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 1024,
40
+ "ignore_attention_mask": false,
41
+ "initializer_range": 0.02,
42
+ "intermediate_size": 4096,
43
+ "layer_norm_eps": 1e-05,
44
+ "max_position_embeddings": 4098,
45
+ "model_type": "longformer",
46
+ "num_attention_heads": 16,
47
+ "num_hidden_layers": 24,
48
+ "pad_token_id": 1,
49
+ "position_embedding_type": "absolute",
50
+ "sep_token_id": 2,
51
+ "transformers_version": "4.2.2",
52
+ "type_vocab_size": 1,
53
+ "use_cache": true,
54
+ "vocab_size": 50275
55
+ }
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:ec63dc3858c01496e5582b9d685db22c99c25029449b99d16d09c90c4bbc0612
3
+ size 1738682816
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 4096, "name_or_path": "allenai/longformer-large-4096"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff