Hugging Face's logo

Den4ikAI
/
rubert_base_response_ranker

Text Classification
Transformers
PyTorch
Russian
bert
Inference Endpoints
Model card Files Community
1
Den4ikAI commited on
Commit
39139da
•
1 Parent(s): 416cd53

Upload 7 files

Browse files
Files changed (6) hide show
  1. config.json +13 -8
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +3 -3
  5. training_args.bin +1 -1
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,28 +1,33 @@
1
  {
2
- "_name_or_path": "16epoch",
3
  "architectures": [
4
  "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
- "emb_size": 312,
9
- "gradient_checkpointing": false,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
- "hidden_size": 312,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 600,
15
  "layer_norm_eps": 1e-12,
16
- "max_position_embeddings": 2048,
17
  "model_type": "bert",
18
  "num_attention_heads": 12,
19
- "num_hidden_layers": 3,
 
20
  "pad_token_id": 0,
 
 
 
 
 
21
  "position_embedding_type": "absolute",
22
  "problem_type": "single_label_classification",
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.25.0",
25
  "type_vocab_size": 2,
26
  "use_cache": true,
27
- "vocab_size": 83828
28
  }
 
1
  {
2
+ "_name_or_path": "model",
3
  "architectures": [
4
  "BertForSequenceClassification"
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": 768,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
  "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
  "model_type": "bert",
17
  "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
  "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
  "position_embedding_type": "absolute",
27
  "problem_type": "single_label_classification",
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.25.0",
30
  "type_vocab_size": 2,
31
  "use_cache": true,
32
+ "vocab_size": 119547
33
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2056cc46997387ed8565e58c93437317629750a89ea9a4882da38e70d17d4b1c
3
- size 116812255
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:169e897f5cbb1a19647c586f317ed0d3ba3ee353ad32ba2893b0c88893a7bf28
3
+ size 711492725
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -3,12 +3,12 @@
3
  "do_basic_tokenize": true,
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
- "model_max_length": 2048,
7
- "name_or_path": "16epoch",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
- "special_tokens_map_file": null,
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",
 
3
  "do_basic_tokenize": true,
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "model",
8
  "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "model/special_tokens_map.json",
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "BertTokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:725f3ed1e72197d35abcb3152bc4eef346c80c8e1b570b7d370d093c489e7aac
3
  size 3323
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ebe48ba780982a1473816f4be75d03af2811752653b87c0a640fd0fb71bb68a
3
  size 3323
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff