DeepaPeri commited on
Commit
a368898
1 Parent(s): c29716e

Upload 6 files

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-location",
16
+ "2": "B-person",
17
+ "3": "I-person",
18
+ "4": "B-organization",
19
+ "5": "I-location",
20
+ "6": "I-organization"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 4096,
24
+ "label2id": {
25
+ "B-location": 1,
26
+ "B-organization": 4,
27
+ "B-person": 2,
28
+ "I-location": 5,
29
+ "I-organization": 6,
30
+ "I-person": 3,
31
+ "O": 0
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 514,
35
+ "model_type": "xlm-roberta",
36
+ "num_attention_heads": 16,
37
+ "num_hidden_layers": 24,
38
+ "output_past": true,
39
+ "pad_token_id": 1,
40
+ "type_vocab_size": 1,
41
+ "vocab_size": 250002
42
+ }
parameter.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dataset": ["panx_dataset/ru"], "transformers_model": "xlm-roberta-large", "random_seed": 1234, "lr": 1e-05, "total_step": 5000, "warmup_step": 700, "weight_decay": 1e-07, "batch_size": 32, "max_seq_length": 128, "fp16": false, "max_grad_norm": 1.0, "lower_case": false}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95701726e524d85cf5db68f90d747b0537c4e6c4b594e8a911f85598e27bdcbc
3
+ size 2235557289
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
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": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "xlm-roberta-large"}