update tokenizer (fix wrong bos setup)
Browse files- tokenizer.json +4 -63
tokenizer.json
CHANGED
@@ -2329,69 +2329,10 @@
|
|
2329 |
]
|
2330 |
},
|
2331 |
"post_processor": {
|
2332 |
-
"type": "
|
2333 |
-
"
|
2334 |
-
|
2335 |
-
|
2336 |
-
"add_prefix_space": true,
|
2337 |
-
"trim_offsets": false,
|
2338 |
-
"use_regex": true
|
2339 |
-
},
|
2340 |
-
{
|
2341 |
-
"type": "TemplateProcessing",
|
2342 |
-
"single": [
|
2343 |
-
{
|
2344 |
-
"SpecialToken": {
|
2345 |
-
"id": "<|begin_of_text|>",
|
2346 |
-
"type_id": 0
|
2347 |
-
}
|
2348 |
-
},
|
2349 |
-
{
|
2350 |
-
"Sequence": {
|
2351 |
-
"id": "A",
|
2352 |
-
"type_id": 0
|
2353 |
-
}
|
2354 |
-
}
|
2355 |
-
],
|
2356 |
-
"pair": [
|
2357 |
-
{
|
2358 |
-
"SpecialToken": {
|
2359 |
-
"id": "<|begin_of_text|>",
|
2360 |
-
"type_id": 0
|
2361 |
-
}
|
2362 |
-
},
|
2363 |
-
{
|
2364 |
-
"Sequence": {
|
2365 |
-
"id": "A",
|
2366 |
-
"type_id": 0
|
2367 |
-
}
|
2368 |
-
},
|
2369 |
-
{
|
2370 |
-
"SpecialToken": {
|
2371 |
-
"id": "<|begin_of_text|>",
|
2372 |
-
"type_id": 1
|
2373 |
-
}
|
2374 |
-
},
|
2375 |
-
{
|
2376 |
-
"Sequence": {
|
2377 |
-
"id": "B",
|
2378 |
-
"type_id": 1
|
2379 |
-
}
|
2380 |
-
}
|
2381 |
-
],
|
2382 |
-
"special_tokens": {
|
2383 |
-
"<|begin_of_text|>": {
|
2384 |
-
"id": "<|begin_of_text|>",
|
2385 |
-
"ids": [
|
2386 |
-
128000
|
2387 |
-
],
|
2388 |
-
"tokens": [
|
2389 |
-
"<|begin_of_text|>"
|
2390 |
-
]
|
2391 |
-
}
|
2392 |
-
}
|
2393 |
-
}
|
2394 |
-
]
|
2395 |
},
|
2396 |
"decoder": {
|
2397 |
"type": "ByteLevel",
|
|
|
2329 |
]
|
2330 |
},
|
2331 |
"post_processor": {
|
2332 |
+
"type": "ByteLevel",
|
2333 |
+
"add_prefix_space": true,
|
2334 |
+
"trim_offsets": false,
|
2335 |
+
"use_regex": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2336 |
},
|
2337 |
"decoder": {
|
2338 |
"type": "ByteLevel",
|