Jinendran commited on
Commit
407bf9b
·
verified ·
1 Parent(s): ba36f47

Upload folder using huggingface_hub

Browse files
jie_checkpoints/checkpoint-2000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
jie_checkpoints/checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe2c3aa64cf154c9c9a9d6349778291668f2bb46751fad3b97857d1fe0e43bc
3
+ size 1419322880
jie_checkpoints/checkpoint-2000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
jie_checkpoints/checkpoint-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
jie_checkpoints/checkpoint-2000/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
jie_checkpoints/checkpoint-2000/vocab.json ADDED
The diff for this file is too large to render. See raw diff