codebyzeb commited on
Commit
25f80fd
·
verified ·
1 Parent(s): 2daf015

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -39,3 +39,4 @@ frequency_256000/tokenizer filter=lfs diff=lfs merge=lfs -text
39
  frequency_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  fw57M_Entropy_frequency-mean-post-merge_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  fw57M_Surprisal_frequency-mean-post-merge_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
39
  frequency_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  fw57M_Entropy_frequency-mean-post-merge_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
41
  fw57M_Surprisal_frequency-mean-post-merge_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ fw57M_Surprisal_min-mean-post-merge_256000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
fw57M_Surprisal_min-mean-post-merge_256000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
fw57M_Surprisal_min-mean-post-merge_256000/merges_data.csv ADDED
The diff for this file is too large to render. See raw diff
 
fw57M_Surprisal_min-mean-post-merge_256000/special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "eos_token": "<|endoftext|>",
3
+ "pad_token": "<|padding|>"
4
+ }
fw57M_Surprisal_min-mean-post-merge_256000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ac5740de0ed0aa93663423ac3d4d4daf56e554464b806cb0fc03208641e8e1
3
+ size 17754512
fw57M_Surprisal_min-mean-post-merge_256000/tokenizer_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|padding|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": null,
22
+ "clean_up_tokenization_spaces": false,
23
+ "eos_token": "<|endoftext|>",
24
+ "extra_special_tokens": {},
25
+ "model_max_length": 1000000000000000019884624838656,
26
+ "pad_token": "<|padding|>",
27
+ "tokenizer_class": "PreTrainedTokenizer",
28
+ "unk_token": null
29
+ }
fw57M_Surprisal_min-mean-post-merge_256000/vocab.json ADDED
The diff for this file is too large to render. See raw diff