mark-rtb commited on
Commit
3973a46
1 Parent(s): 6a7bba4

HRBert-mini

Browse files
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+
3
+ language: ["ru", "en", "be", "bg", "uk", "ro", "kz", "tg", "tat", "sv", "sl", "sr", "uz", "es", "fi"]
4
+
5
+ tags:
6
+
7
+ - russian
8
+
9
+ - fill-mask
10
+
11
+ - pretraining
12
+
13
+ - embeddings
14
+
15
+ - masked-lm
16
+
17
+
18
+ license: mit
19
+
20
+ widget:
21
+
22
+ - text: "[MASK] категории С"
23
+
24
+ ---
25
+
26
+ This is a distilled Herbert model for an mlm task.
27
+
28
+
29
+ Sentence embeddings can be produced as follows:
30
+
31
+ ```python
32
+
33
+ # pip install transformers
34
+
35
+ from transformers import pipeline
36
+
37
+
38
+ fill_mask = pipeline(
39
+ "fill-mask",
40
+ model='RabotaRu/HRBert-mini',
41
+ tokenizer='RabotaRu/HRBert-mini'
42
+ )
43
+
44
+ fill_mask('требуется <mask> менеджер')
45
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "emb_size": 384,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 384,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 3,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.11.3",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 200001
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb723ea01cb97ca3041bd5a345502a97adf43f1065b0babd687007e1b80fa4e4
3
+ size 321258804
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "cls_token": "<cls>", "mask_token": "<mask>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"special_tokens_map_file": "./HRBert2/special_tokens_map.json", "name_or_path": "./HRBert2", "tokenizer_class": "PreTrainedTokenizerFast"}