Commit
•
e94f2b1
1
Parent(s):
c919139
Upload tokenizer.json
Browse filesThe persisted `tokenizer.json` does not have the template processor for adding special tokens. `transformers` overrides the processor on load, but when loading `tokenizer.json` directly with the Rust tokenizers it's nice to have the processor there already (which worked so far in case of other models). This basically re-saves the tokenizer to match exactly what is loaded by `transformers`.
---
Generated with:
```python
from transformers import AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-1.3b-base")
assert tokenizer.is_fast
tokenizer.save_pretrained("...")
```
- tokenizer.json +52 -4
tokenizer.json
CHANGED
@@ -254,10 +254,58 @@
|
|
254 |
]
|
255 |
},
|
256 |
"post_processor": {
|
257 |
-
"type": "
|
258 |
-
"
|
259 |
-
|
260 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
261 |
},
|
262 |
"decoder": {
|
263 |
"type": "ByteLevel",
|
|
|
254 |
]
|
255 |
},
|
256 |
"post_processor": {
|
257 |
+
"type": "TemplateProcessing",
|
258 |
+
"single": [
|
259 |
+
{
|
260 |
+
"SpecialToken": {
|
261 |
+
"id": "<|begin▁of▁sentence|>",
|
262 |
+
"type_id": 0
|
263 |
+
}
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"Sequence": {
|
267 |
+
"id": "A",
|
268 |
+
"type_id": 0
|
269 |
+
}
|
270 |
+
}
|
271 |
+
],
|
272 |
+
"pair": [
|
273 |
+
{
|
274 |
+
"SpecialToken": {
|
275 |
+
"id": "<|begin▁of▁sentence|>",
|
276 |
+
"type_id": 0
|
277 |
+
}
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"Sequence": {
|
281 |
+
"id": "A",
|
282 |
+
"type_id": 0
|
283 |
+
}
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"SpecialToken": {
|
287 |
+
"id": "<|begin▁of▁sentence|>",
|
288 |
+
"type_id": 1
|
289 |
+
}
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"Sequence": {
|
293 |
+
"id": "B",
|
294 |
+
"type_id": 1
|
295 |
+
}
|
296 |
+
}
|
297 |
+
],
|
298 |
+
"special_tokens": {
|
299 |
+
"<|begin▁of▁sentence|>": {
|
300 |
+
"id": "<|begin▁of▁sentence|>",
|
301 |
+
"ids": [
|
302 |
+
32013
|
303 |
+
],
|
304 |
+
"tokens": [
|
305 |
+
"<|begin▁of▁sentence|>"
|
306 |
+
]
|
307 |
+
}
|
308 |
+
}
|
309 |
},
|
310 |
"decoder": {
|
311 |
"type": "ByteLevel",
|