lucasbiagettia commited on
Commit
99bebb6
1 Parent(s): 8da1793

Upload tokenizer (#1)

Browse files

- Upload tokenizer (15ca6f5082a52890810c652ff4d248384cdf0d41)

Files changed (6) hide show
  1. README.md +1 -1
  2. merges.txt +0 -0
  3. special_tokens_map.json +23 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +22 -0
  6. vocab.json +0 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
3
- base_model: EleutherAI/gpt-neo-125m
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: gpt-neo-borges
8
  results: []
 
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: EleutherAI/gpt-neo-125m
6
  model-index:
7
  - name: gpt-neo-borges
8
  results: []
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": null,
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff