Konrad Wojtasik commited on
Commit
5c7634e
1 Parent(s): 630fb0f
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "azwierzc/herbert-large-poquad",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 1,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "tokenizer_class": "HerbertTokenizerFast",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.20.1",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 50000
32
+ }
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 sha256:9e43b3cfa55eb6c7869441aee30f73e8ae3c9ce28fdf451465ee774580b7033e
3
+ size 1416297329
special_tokens_map.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "mask_token": "<mask>",
5
+ "pad_token": "<pad>",
6
+ "sep_token": "</s>",
7
+ "unk_token": "<unk>"
8
+ }
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
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "do_lowercase_and_remove_accent": false,
6
+ "id2lang": null,
7
+ "lang2id": null,
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "name_or_path": "azwierzc/herbert-large-poquad",
11
+ "pad_token": "<pad>",
12
+ "sep_token": "</s>",
13
+ "special_tokens_map_file": "/home/azwierzchowska/.cache/huggingface/hub/models--allegro--herbert-large-cased/snapshots/8d0fa3bc0566c3a332bec0d471c8d8c37b5cbb90/special_tokens_map.json",
14
+ "tokenizer_class": "HerbertTokenizer",
15
+ "unk_token": "<unk>"
16
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff