amitness commited on
Commit
c68d725
1 Parent(s): 086b0c4

Add first version of nepbert and tokenizer

Browse files
Files changed (5) hide show
  1. config.json +23 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. training_args.bin +3 -0
  5. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "type_vocab_size": 1,
22
+ "vocab_size": 52000
23
+ }
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 sha256:315f7ad491ea89c8e1d47c4df4c5118e79f0b63ab9efa0ce9bc0a5f9f5560dad
3
+ size 334066395
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e34e12ffd0b9fb1a4670a23b2d09a04c12c58cdec40c8930c5ec75fb552fd3
3
+ size 1903
vocab.json ADDED
The diff for this file is too large to render. See raw diff