Aleksandar commited on
Commit
4e75a39
1 Parent(s): 192137a

Roberta model called SRoBERTa trained on WOL dataset (OSCAR + Leipzig + srWac) for Serbian language. Attention heads distilled 6, batch size 64, group size 64, epochs 2, test split 0.05(~1mil groups)

Browse files
Files changed (3) hide show
  1. config.json +25 -0
  2. pytorch_model.bin +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 2,
8
+ "gradient_checkpointing": false,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.8.2",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 48000
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d6251e1f8cc0a6dc6b494e952a1413792f71ce3e78a211a26d883c6cbaa0c5
3
+ size 321760363
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96bbea3cb7f41d85346a77688e8deb7feb8fbca21221425e774b101409de381a
3
+ size 2671