delmaksym commited on
Commit
eff49dc
1 Parent(s): 2b447f4
Files changed (2) hide show
  1. config.json +33 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "scale_normformer/checkpoint-1000000",
3
+ "architectures": [
4
+ "XLMRobertaModel"
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-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "scale_attn": true,
23
+ "scale_fc": true,
24
+ "scale_heads": true,
25
+ "scale_post": false,
26
+ "scale_pre": true,
27
+ "scale_resids": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.19.0.dev0",
30
+ "type_vocab_size": 2,
31
+ "use_cache": true,
32
+ "vocab_size": 52005
33
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec629f6dfed5c2e62c5822bd21297925ff2c64e9827a54ef1bfe4bbcc06b3ea
3
+ size 504413221