himani commited on
Commit
a4dd18b
1 Parent(s): 6ffb99f
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 64000, "</s>": 64001, "<2shuf>": 64002, "<2as>": 64003, "<2bn>": 64004, "<2en>": 64005, "<2gu>": 64006, "<2hi>": 64007, "<2kn>": 64008, "<2ml>": 64009, "<2mr>": 64010, "<2or>": 64011, "<2pa>": 64012, "<2ta>": 64013, "<2te>": 64014}
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.1,
3
+ "activation_function": "gelu",
4
+ "architectures": [
5
+ "MBartForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 64000,
9
+ "d_model": 1024,
10
+ "classifier_dropout": 0.0,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.0,
14
+ "decoder_layers": 6,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0.0,
19
+ "encoder_layers": 6,
20
+ "eos_token_id": 64001,
21
+ "gradient_checkpointing": false,
22
+ "init_std": 0.02,
23
+ "is_encoder_decoder": true,
24
+ "max_position_embeddings": 1024,
25
+ "model_type": "mbart",
26
+ "num_hidden_layers": 6,
27
+ "pad_token_id": 0,
28
+ "scale_embedding": false,
29
+ "transformers_version": "4.3.2",
30
+ "use_cache": true,
31
+ "vocab_size": 64015,
32
+ "tokenizer_class": "AlbertTokenizer"
33
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s>", "</s>", "<2as>", "<2bn>", "<2en>", "<2gu>", "<2hi>", "<2kn>", "<2ml>", "<2mr>", "<2or>", "<2pa>", "<2ta>", "<2te>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d922f1b9444ae05eab57f3f0a9d60d4147e905a160f07c3b08116e7b3b8c6a
3
+ size 1803730
spiece.vocab ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "use_fast": false, "special_tokens_map_file": "albert-indic64k/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "albert-indic64k"}