Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +12 -2
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 50,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 50
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,16 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
-
"name_or_path": "
|
|
|
|
|
|
|
|
|
|
| 4 |
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--gogamza--kobart-base-v2/snapshots/f9f2ec35d3c32a1ecc7a3281f9626b7ec1913fed/special_tokens_map.json",
|
| 5 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_special_tokens": true,
|
| 3 |
+
"bos_token": "",
|
| 4 |
+
"eos_token": "",
|
| 5 |
+
"mask_token": "",
|
| 6 |
+
"max_len": 40,
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"name_or_path": "just-final/BART_poem",
|
| 9 |
+
"pad_token": "",
|
| 10 |
+
"padding": "max_length",
|
| 11 |
+
"return_tensors": "pt",
|
| 12 |
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--gogamza--kobart-base-v2/snapshots/f9f2ec35d3c32a1ecc7a3281f9626b7ec1913fed/special_tokens_map.json",
|
| 13 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 14 |
+
"truncation": true,
|
| 15 |
+
"unk_token": ""
|
| 16 |
}
|