tamoghna commited on
Commit
83b0712
·
verified ·
1 Parent(s): 1f1bb67

Upload 6 files

Browse files
Files changed (6) hide show
  1. __init__.py +0 -0
  2. config.json +17 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer_config.json +11 -0
  6. vocab.json +0 -0
__init__.py ADDED
File without changes
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": ["SmallTransformer"],
3
+ "model_type": "small_transformer",
4
+ "vocab_size": 80000,
5
+ "d_model": 256,
6
+ "nhead": 8,
7
+ "num_encoder_layers": 3,
8
+ "num_decoder_layers": 3,
9
+ "dim_feedforward": 512,
10
+ "dropout": 0.1,
11
+ "pad_token_id": 0,
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 2,
14
+ "max_position_embeddings": 512,
15
+ "torch_dtype": "float32",
16
+ "transformers_version": "4.36.0"
17
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>",
6
+ "mask_token": "<mask>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizer_class": "ByteLevelBPETokenizer",
3
+ "add_prefix_space": false,
4
+ "bos_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "pad_token": "<pad>",
7
+ "unk_token": "<unk>",
8
+ "mask_token": "<mask>",
9
+ "additional_special_tokens": ["<hi>", "<bn>"],
10
+ "model_max_length": 64
11
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff