Upload tokenizer
Browse files- special_tokens_map.json +3 -1
- tokenizer.json +6 -1
- tokenizer_config.json +5 -2
special_tokens_map.json
CHANGED
|
@@ -6,6 +6,8 @@
|
|
| 6 |
"<|tel|>",
|
| 7 |
"<|rrn|>"
|
| 8 |
],
|
|
|
|
| 9 |
"eos_token": "<|endoftext|>",
|
| 10 |
-
"pad_token": "<|endoftext|>"
|
|
|
|
| 11 |
}
|
|
|
|
| 6 |
"<|tel|>",
|
| 7 |
"<|rrn|>"
|
| 8 |
],
|
| 9 |
+
"bos_token": "<|endoftext|>",
|
| 10 |
"eos_token": "<|endoftext|>",
|
| 11 |
+
"pad_token": "<|endoftext|>",
|
| 12 |
+
"unk_token": "<|endoftext|>"
|
| 13 |
}
|
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 2048,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,10 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
-
"model_max_length":
|
| 5 |
"pad_token": "<|endoftext|>",
|
| 6 |
-
"tokenizer_class": "
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "<|endoftext|>",
|
| 8 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 9 |
+
"unk_token": "<|endoftext|>"
|
| 10 |
}
|