GhadeerALbadani commited on
Commit
abbae5c
·
1 Parent(s): aed883b

Upload 6 files

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|unknown|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|startoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "name_or_path": "aubmindlab/aragpt2-base",
6
+ "pad_token": "<|pad|>",
7
+ "special_tokens_map_file": null,
8
+ "tokenizer_class": "GPT2Tokenizer",
9
+ "unk_token": "<|unknown|>"
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e0a5527567096e6c5c6085ea21fab26696b5810f628b140beb91786dcff408
3
+ size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff