rajeshradhakrishnan commited on
Commit
0d8b9a7
1 Parent(s): f93435f

First version of the malayalam_2020_wiki model.

Browse files
Files changed (5) hide show
  1. config.json +27 -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 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
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": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.10.0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 52000
27
+ }
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 sha256:9e5fb716112ea1b2844624efb4af6deae74f845b6597cf851d7a90bc1ab55a4a
3
+ size 334055467
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16f49a9e521175c85fe3e2fddfc78302353e958359623774ed27fa19e8bd612
3
+ size 2671
vocab.json ADDED
The diff for this file is too large to render. See raw diff