asahi417 commited on
Commit
6c55a9a
1 Parent(s): ce83552

Upload XLMRobertaForMaskedLM

Browse files
Files changed (2) hide show
  1. config.json +49 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ckpts/xlm-roberta-base-trimmed-en-60000",
3
+ "architectures": [
4
+ "XLMRobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.26.1",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 60002,
28
+ "vocabtrimmer": {
29
+ "mining_config": {
30
+ "dataset": "vocabtrimmer/mc4_validation",
31
+ "dataset_column": "text",
32
+ "dataset_name": "en",
33
+ "dataset_split": "validation",
34
+ "language": "en",
35
+ "min_frequency": 2,
36
+ "target_vocab_size": 60000
37
+ },
38
+ "stats": {
39
+ "compression_rate_embedding": 24.00060799513604,
40
+ "compression_rate_full": 47.49819351887747,
41
+ "parameter_size_embedding/raw": 192001536,
42
+ "parameter_size_embedding/trimmed": 46081536,
43
+ "parameter_size_full/raw": 278295186,
44
+ "parameter_size_full/trimmed": 132185186,
45
+ "vocab_size/raw": 250002,
46
+ "vocab_size/trimmed": 60002
47
+ }
48
+ }
49
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e37acd117a03a2a733eeafcfb753c54068570f41385e7d572c9c7cceb7bec59
3
+ size 528809899