Add custom processor
Browse files- processor_config.json +14 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -0
- vocab.json +0 -0
processor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"mean": [
|
| 3 |
+
0.48145466,
|
| 4 |
+
0.4578275,
|
| 5 |
+
0.40821073
|
| 6 |
+
],
|
| 7 |
+
"processor_class": "SimpleStarVectorProcessor",
|
| 8 |
+
"size": 224,
|
| 9 |
+
"std": [
|
| 10 |
+
0.26862954,
|
| 11 |
+
0.26130258,
|
| 12 |
+
0.27577711
|
| 13 |
+
]
|
| 14 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -212,8 +212,10 @@
|
|
| 212 |
"clean_up_tokenization_spaces": true,
|
| 213 |
"eos_token": "<|endoftext|>",
|
| 214 |
"errors": "replace",
|
|
|
|
| 215 |
"model_max_length": 1000000000000000019884624838656,
|
| 216 |
"pad_token": "[PAD]",
|
|
|
|
| 217 |
"tokenizer_class": "GPT2Tokenizer",
|
| 218 |
"unk_token": "<|endoftext|>",
|
| 219 |
"vocab_size": 49152
|
|
|
|
| 212 |
"clean_up_tokenization_spaces": true,
|
| 213 |
"eos_token": "<|endoftext|>",
|
| 214 |
"errors": "replace",
|
| 215 |
+
"extra_special_tokens": {},
|
| 216 |
"model_max_length": 1000000000000000019884624838656,
|
| 217 |
"pad_token": "[PAD]",
|
| 218 |
+
"processor_class": "SimpleStarVectorProcessor",
|
| 219 |
"tokenizer_class": "GPT2Tokenizer",
|
| 220 |
"unk_token": "<|endoftext|>",
|
| 221 |
"vocab_size": 49152
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|