sdadas commited on
Commit
6a0c72f
1 Parent(s): 75025cc

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 4096,
17
+ "label2id": {
18
+ "LABEL_0": 0
19
+ },
20
+ "layer_norm_eps": 1e-05,
21
+ "max_position_embeddings": 514,
22
+ "model_type": "roberta",
23
+ "num_attention_heads": 16,
24
+ "num_hidden_layers": 24,
25
+ "pad_token_id": 1,
26
+ "position_embedding_type": "absolute",
27
+ "problem_type": "regression",
28
+ "torch_dtype": "float16",
29
+ "transformers_version": "4.32.1",
30
+ "type_vocab_size": 1,
31
+ "use_cache": true,
32
+ "vocab_size": 128001
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f68d745135b80d41e88fde1f6aee3754da4f7cd1105b5c2d8174d9d0ad658a79
3
+ size 870060910
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
+ "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
15
+ }
unigram.json ADDED
The diff for this file is too large to render. See raw diff