Question Answering
Transformers
Safetensors
English
doge
text-generation
custom_code
JingzeShi commited on
Commit
deff97f
verified
1 Parent(s): 1b67b34

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +23 -23
  2. tokenizer.json +8 -8
  3. tokenizer_config.json +0 -0
special_tokens_map.json CHANGED
@@ -1,23 +1,23 @@
1
- {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|end_of_text|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|finetune_right_pad_id|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- }
23
- }
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json CHANGED
@@ -2272,8 +2272,8 @@
2272
  "special": true
2273
  },
2274
  {
2275
- "id": 252,
2276
- "content": "<|reserved_special_token_244|>",
2277
  "single_word": false,
2278
  "lstrip": false,
2279
  "rstrip": false,
@@ -2281,8 +2281,8 @@
2281
  "special": true
2282
  },
2283
  {
2284
- "id": 253,
2285
- "content": "<|reserved_special_token_245|>",
2286
  "single_word": false,
2287
  "lstrip": false,
2288
  "rstrip": false,
@@ -2290,8 +2290,8 @@
2290
  "special": true
2291
  },
2292
  {
2293
- "id": 254,
2294
- "content": "<|reserved_special_token_246|>",
2295
  "single_word": false,
2296
  "lstrip": false,
2297
  "rstrip": false,
@@ -2299,8 +2299,8 @@
2299
  "special": true
2300
  },
2301
  {
2302
- "id": 255,
2303
- "content": "<|reserved_special_token_247|>",
2304
  "single_word": false,
2305
  "lstrip": false,
2306
  "rstrip": false,
 
2272
  "special": true
2273
  },
2274
  {
2275
+ "id": 32768,
2276
+ "content": "<think>",
2277
  "single_word": false,
2278
  "lstrip": false,
2279
  "rstrip": false,
 
2281
  "special": true
2282
  },
2283
  {
2284
+ "id": 32769,
2285
+ "content": "</think>",
2286
  "single_word": false,
2287
  "lstrip": false,
2288
  "rstrip": false,
 
2290
  "special": true
2291
  },
2292
  {
2293
+ "id": 32770,
2294
+ "content": "<answer>",
2295
  "single_word": false,
2296
  "lstrip": false,
2297
  "rstrip": false,
 
2299
  "special": true
2300
  },
2301
  {
2302
+ "id": 32771,
2303
+ "content": "</answer>",
2304
  "single_word": false,
2305
  "lstrip": false,
2306
  "rstrip": false,
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff