Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +27 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": true,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"max_length": 32,
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"pad_to_multiple_of": null,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"pad_token_type_id": 0,
|
| 21 |
+
"padding_side": "right",
|
| 22 |
+
"stride": 0,
|
| 23 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 24 |
+
"truncation_side": "right",
|
| 25 |
+
"truncation_strategy": "longest_first",
|
| 26 |
+
"unk_token": "<|endoftext|>"
|
| 27 |
+
}
|