Locutusque
commited on
Commit
•
2d1692a
1
Parent(s):
2e8c387
Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
@@ -317,8 +317,15 @@
|
|
317 |
"bos_token": "<|endoftext|>",
|
318 |
"clean_up_tokenization_spaces": true,
|
319 |
"eos_token": "<|endoftext|>",
|
|
|
320 |
"model_max_length": 2048,
|
|
|
321 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
322 |
"tokenizer_class": "CodeGenTokenizer",
|
|
|
|
|
323 |
"unk_token": "<|endoftext|>"
|
324 |
}
|
|
|
317 |
"bos_token": "<|endoftext|>",
|
318 |
"clean_up_tokenization_spaces": true,
|
319 |
"eos_token": "<|endoftext|>",
|
320 |
+
"max_length": 512,
|
321 |
"model_max_length": 2048,
|
322 |
+
"pad_to_multiple_of": null,
|
323 |
"pad_token": "<|endoftext|>",
|
324 |
+
"pad_token_type_id": 0,
|
325 |
+
"padding_side": "right",
|
326 |
+
"stride": 0,
|
327 |
"tokenizer_class": "CodeGenTokenizer",
|
328 |
+
"truncation_side": "right",
|
329 |
+
"truncation_strategy": "longest_first",
|
330 |
"unk_token": "<|endoftext|>"
|
331 |
}
|