Initial release: UnitronX Tokenizer 32k v1
Browse files- merges.txt +0 -0
- meta.json +25 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- unitronx.tiktoken.json +0 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
meta.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name": "UnitronX-Tokenizer-32k-v1",
|
| 3 |
+
"saved_at": "2025-11-06T21:44:44Z",
|
| 4 |
+
"vocab_size": 32000,
|
| 5 |
+
"special_tokens": [
|
| 6 |
+
"<unk>",
|
| 7 |
+
"<s>",
|
| 8 |
+
"</s>",
|
| 9 |
+
"<pad>",
|
| 10 |
+
"<mask>",
|
| 11 |
+
"<eot>",
|
| 12 |
+
"<URL>",
|
| 13 |
+
"<EMAIL>",
|
| 14 |
+
"<PATH>",
|
| 15 |
+
"<HEX>",
|
| 16 |
+
"<UUID>",
|
| 17 |
+
"<HANDLE>",
|
| 18 |
+
"<HASHTAG>",
|
| 19 |
+
"<NUM_2D>",
|
| 20 |
+
"<NUM_4D>",
|
| 21 |
+
"<NUM_N>"
|
| 22 |
+
],
|
| 23 |
+
"byte_fallback": true,
|
| 24 |
+
"sha256": "b69c786fa3cee01dd1f60835cd1b5081efd197c6ea84214fc2ba0d605c229df0"
|
| 25 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"additional_special_tokens": [
|
| 8 |
+
"<eot>",
|
| 9 |
+
"<URL>",
|
| 10 |
+
"<EMAIL>",
|
| 11 |
+
"<PATH>",
|
| 12 |
+
"<HEX>",
|
| 13 |
+
"<UUID>",
|
| 14 |
+
"<HANDLE>",
|
| 15 |
+
"<HASHTAG>",
|
| 16 |
+
"<NUM_2D>",
|
| 17 |
+
"<NUM_4D>",
|
| 18 |
+
"<NUM_N>"
|
| 19 |
+
]
|
| 20 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_max_length": 4096,
|
| 3 |
+
"padding_side": "right",
|
| 4 |
+
"truncation_side": "right",
|
| 5 |
+
"add_prefix_space": true,
|
| 6 |
+
"name_or_path": "UnitronX-Tokenizer-32k-v1",
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"eos_token": "</s>"
|
| 9 |
+
}
|
unitronx.tiktoken.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|