Milan Straka commited on
Commit
b4fda3e
1 Parent(s): e75fab4

Add RobeCzech checkpoint.

Browse files
Files changed (6) hide show
  1. config.json +22 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. tf_model.h5 +3 -0
  5. tokenizer_config.json +1 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "type_vocab_size": 1,
21
+ "vocab_size": 51961
22
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ada3c49cf56eda3228362a987ef813d4cec59bbb70730237d0d86bad6f0111c
3
+ size 506663689
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a135a8b68b32fba27b5950b203787cfb5f06b714122ecc216b1b2a83808e27c0
3
+ size 667860748
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "sep_token": "[SEP]", "cls_token": "[CLS]", "unk_token": "[UNK]", "pad_token": "[PAD]", "mask_token": "[MASK]", "add_prefix_space": false}
vocab.json ADDED
The diff for this file is too large to render. See raw diff