Upload tokenizer.json
Browse files- tokenizer.json +63 -4
tokenizer.json
CHANGED
@@ -2347,10 +2347,69 @@
|
|
2347 |
]
|
2348 |
},
|
2349 |
"post_processor": {
|
2350 |
-
"type": "
|
2351 |
-
"
|
2352 |
-
|
2353 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2354 |
},
|
2355 |
"decoder": {
|
2356 |
"type": "ByteLevel",
|
|
|
2347 |
]
|
2348 |
},
|
2349 |
"post_processor": {
|
2350 |
+
"type": "Sequence",
|
2351 |
+
"processors": [
|
2352 |
+
{
|
2353 |
+
"type": "ByteLevel",
|
2354 |
+
"add_prefix_space": true,
|
2355 |
+
"trim_offsets": false,
|
2356 |
+
"use_regex": true
|
2357 |
+
},
|
2358 |
+
{
|
2359 |
+
"type": "TemplateProcessing",
|
2360 |
+
"single": [
|
2361 |
+
{
|
2362 |
+
"SpecialToken": {
|
2363 |
+
"id": "<|begin_of_text|>",
|
2364 |
+
"type_id": 0
|
2365 |
+
}
|
2366 |
+
},
|
2367 |
+
{
|
2368 |
+
"Sequence": {
|
2369 |
+
"id": "A",
|
2370 |
+
"type_id": 0
|
2371 |
+
}
|
2372 |
+
}
|
2373 |
+
],
|
2374 |
+
"pair": [
|
2375 |
+
{
|
2376 |
+
"SpecialToken": {
|
2377 |
+
"id": "<|begin_of_text|>",
|
2378 |
+
"type_id": 0
|
2379 |
+
}
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"Sequence": {
|
2383 |
+
"id": "A",
|
2384 |
+
"type_id": 0
|
2385 |
+
}
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"SpecialToken": {
|
2389 |
+
"id": "<|begin_of_text|>",
|
2390 |
+
"type_id": 1
|
2391 |
+
}
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"Sequence": {
|
2395 |
+
"id": "B",
|
2396 |
+
"type_id": 1
|
2397 |
+
}
|
2398 |
+
}
|
2399 |
+
],
|
2400 |
+
"special_tokens": {
|
2401 |
+
"<|begin_of_text|>": {
|
2402 |
+
"id": "<|begin_of_text|>",
|
2403 |
+
"ids": [
|
2404 |
+
128000
|
2405 |
+
],
|
2406 |
+
"tokens": [
|
2407 |
+
"<|begin_of_text|>"
|
2408 |
+
]
|
2409 |
+
}
|
2410 |
+
}
|
2411 |
+
}
|
2412 |
+
]
|
2413 |
},
|
2414 |
"decoder": {
|
2415 |
"type": "ByteLevel",
|