mrm8488 commited on
Commit
db1df4e
1 Parent(s): 47455f1

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<fim-middle>": 49154,
3
+ "<fim-pad>": 49156,
4
+ "<fim-prefix>": 49153,
5
+ "<fim-suffix>": 49155,
6
+ "<|endoftext|>": 49152
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim-prefix>",
5
+ "<fim-middle>",
6
+ "<fim-suffix>",
7
+ "<fim-pad>"
8
+ ],
9
+ "bos_token": "<|endoftext|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "unk_token": "<|endoftext|>"
12
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "errors": "replace",
6
+ "model_max_length": 2048,
7
+ "name_or_path": "bigcode/santacoder",
8
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--bigcode--santacoder/snapshots/636ad0a694975c25bdb8a16fb8ffda275525a2a8/special_tokens_map.json",
9
+ "tokenizer_class": "GPT2Tokenizer",
10
+ "unk_token": "<|endoftext|>"
11
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff