m3hrdadfi commited on
Commit
c4e13ba
1 Parent(s): 7836765

Initialized

Browse files
README.md ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: fa
3
+ license: apache-2.0
4
+ ---
5
+
6
+
7
+ # DistilBERT
8
+ This model can tackle the zero-width non-joiner character for Persian writing. Also, the model was trained on new multi-types corpora with a new set of vocabulary.
9
+
10
+
11
+ ## Questions?
12
+ Post a Github issue on the [ParsRoBERTa Issues](https://github.com/hooshvare/roberta/issues) repo.
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": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "transformers_version": "4.2.2",
22
+ "type_vocab_size": 1,
23
+ "use_cache": true,
24
+ "vocab_size": 42000
25
+ }
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 sha256:2293b33bbb807e74906994ef6a6c7537856f82cdec73f097c6f461f333db7f0f
3
+ size 473455707
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>",
5
+ "sep_token": "</s>",
6
+ "pad_token": "<pad>",
7
+ "cls_token": "<s>",
8
+ "mask_token": {
9
+ "content": "<mask>",
10
+ "single_word": false,
11
+ "lstrip": true,
12
+ "rstrip": false,
13
+ "normalized": false
14
+ }
15
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bcc36b6c014a1a667fbe437d50949852d61069f231014729c82a00df56c902
3
+ size 602663104
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "unk_token": "<unk>",
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "add_prefix_space": false,
6
+ "errors": "replace",
7
+ "sep_token": "</s>",
8
+ "cls_token": "<s>",
9
+ "pad_token": "<pad>",
10
+ "mask_token": "<mask>",
11
+ "special_tokens_map_file": null
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff