Hugging Face's logo

cuba6112
/
orion

Question Answering
Transformers
TensorBoard
Safetensors
English
gpt2
text-generation
fine-tuned
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
cuba6112 commited on
Commit
e2a72ff
•
1 Parent(s): 1588475

Upload tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +24 -24
  3. tokenizer_config.json +22 -22
  4. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,24 +1,24 @@
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
- "pad_token": "<|endoftext|>",
17
- "unk_token": {
18
- "content": "<|endoftext|>",
19
- "lstrip": false,
20
- "normalized": true,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
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
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json CHANGED
@@ -1,22 +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": 1024,
19
- "pad_token": "<|endoftext|>",
20
- "tokenizer_class": "GPT2Tokenizer",
21
- "unk_token": "<|endoftext|>"
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": 1024,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff