Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +28 -7
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
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 |
{
|
@@ -304,6 +299,33 @@
|
|
304 |
"rstrip": false,
|
305 |
"normalized": false,
|
306 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
307 |
}
|
308 |
],
|
309 |
"normalizer": null,
|
@@ -341,7 +363,6 @@
|
|
341 |
"end_of_word_suffix": "",
|
342 |
"fuse_unk": false,
|
343 |
"byte_fallback": false,
|
344 |
-
"ignore_merges": false,
|
345 |
"vocab": {
|
346 |
"!": 0,
|
347 |
"\"": 1,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
299 |
"rstrip": false,
|
300 |
"normalized": false,
|
301 |
"special": true
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"id": 100289,
|
305 |
+
"content": "<s>",
|
306 |
+
"single_word": false,
|
307 |
+
"lstrip": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"normalized": false,
|
310 |
+
"special": true
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"id": 100290,
|
314 |
+
"content": "</s>",
|
315 |
+
"single_word": false,
|
316 |
+
"lstrip": false,
|
317 |
+
"rstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"special": true
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"id": 100291,
|
323 |
+
"content": "<unk>",
|
324 |
+
"single_word": false,
|
325 |
+
"lstrip": false,
|
326 |
+
"rstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"special": true
|
329 |
}
|
330 |
],
|
331 |
"normalizer": null,
|
|
|
363 |
"end_of_word_suffix": "",
|
364 |
"fuse_unk": false,
|
365 |
"byte_fallback": false,
|
|
|
366 |
"vocab": {
|
367 |
"!": 0,
|
368 |
"\"": 1,
|