Upload tokenizer
Browse files- added_tokens.json +12 -12
- tokenizer_config.json +16 -16
added_tokens.json
CHANGED
@@ -37,16 +37,16 @@
|
|
37 |
" ": 50259,
|
38 |
" ": 50258,
|
39 |
" ": 50257,
|
40 |
-
"<PAD>":
|
41 |
-
"<|end_of_turn|>":
|
42 |
-
"<|end|>":
|
43 |
-
"<|function_call|>":
|
44 |
-
"<|response|>":
|
45 |
-
"<|thoughts|>":
|
46 |
-
"Azma":
|
47 |
-
"Azma:":
|
48 |
-
"Observation:":
|
49 |
-
"Reference:":
|
50 |
-
"System:":
|
51 |
-
"User:":
|
52 |
}
|
|
|
37 |
" ": 50259,
|
38 |
" ": 50258,
|
39 |
" ": 50257,
|
40 |
+
"<PAD>": 50296,
|
41 |
+
"<|end_of_turn|>": 50298,
|
42 |
+
"<|end|>": 50297,
|
43 |
+
"<|function_call|>": 50301,
|
44 |
+
"<|response|>": 50305,
|
45 |
+
"<|thoughts|>": 50304,
|
46 |
+
"Azma": 50303,
|
47 |
+
"Azma:": 50302,
|
48 |
+
"Observation:": 50299,
|
49 |
+
"Reference:": 50295,
|
50 |
+
"System:": 50300,
|
51 |
+
"User:": 50306
|
52 |
}
|
tokenizer_config.json
CHANGED
@@ -316,7 +316,7 @@
|
|
316 |
"special": false
|
317 |
},
|
318 |
"50295": {
|
319 |
-
"content": "
|
320 |
"lstrip": false,
|
321 |
"normalized": true,
|
322 |
"rstrip": false,
|
@@ -324,15 +324,15 @@
|
|
324 |
"special": false
|
325 |
},
|
326 |
"50296": {
|
327 |
-
"content": "
|
328 |
"lstrip": false,
|
329 |
-
"normalized":
|
330 |
"rstrip": false,
|
331 |
"single_word": false,
|
332 |
-
"special":
|
333 |
},
|
334 |
"50297": {
|
335 |
-
"content": "
|
336 |
"lstrip": false,
|
337 |
"normalized": true,
|
338 |
"rstrip": false,
|
@@ -340,7 +340,7 @@
|
|
340 |
"special": false
|
341 |
},
|
342 |
"50298": {
|
343 |
-
"content": "
|
344 |
"lstrip": false,
|
345 |
"normalized": true,
|
346 |
"rstrip": false,
|
@@ -348,7 +348,7 @@
|
|
348 |
"special": false
|
349 |
},
|
350 |
"50299": {
|
351 |
-
"content": "
|
352 |
"lstrip": false,
|
353 |
"normalized": true,
|
354 |
"rstrip": false,
|
@@ -356,7 +356,7 @@
|
|
356 |
"special": false
|
357 |
},
|
358 |
"50300": {
|
359 |
-
"content": "
|
360 |
"lstrip": false,
|
361 |
"normalized": true,
|
362 |
"rstrip": false,
|
@@ -364,7 +364,7 @@
|
|
364 |
"special": false
|
365 |
},
|
366 |
"50301": {
|
367 |
-
"content": "<|
|
368 |
"lstrip": false,
|
369 |
"normalized": true,
|
370 |
"rstrip": false,
|
@@ -372,7 +372,7 @@
|
|
372 |
"special": false
|
373 |
},
|
374 |
"50302": {
|
375 |
-
"content": "
|
376 |
"lstrip": false,
|
377 |
"normalized": true,
|
378 |
"rstrip": false,
|
@@ -380,7 +380,7 @@
|
|
380 |
"special": false
|
381 |
},
|
382 |
"50303": {
|
383 |
-
"content": "
|
384 |
"lstrip": false,
|
385 |
"normalized": true,
|
386 |
"rstrip": false,
|
@@ -388,15 +388,15 @@
|
|
388 |
"special": false
|
389 |
},
|
390 |
"50304": {
|
391 |
-
"content": "
|
392 |
"lstrip": false,
|
393 |
-
"normalized":
|
394 |
"rstrip": false,
|
395 |
"single_word": false,
|
396 |
-
"special":
|
397 |
},
|
398 |
"50305": {
|
399 |
-
"content": "
|
400 |
"lstrip": false,
|
401 |
"normalized": true,
|
402 |
"rstrip": false,
|
@@ -404,7 +404,7 @@
|
|
404 |
"special": false
|
405 |
},
|
406 |
"50306": {
|
407 |
-
"content": "
|
408 |
"lstrip": false,
|
409 |
"normalized": true,
|
410 |
"rstrip": false,
|
|
|
316 |
"special": false
|
317 |
},
|
318 |
"50295": {
|
319 |
+
"content": "Reference:",
|
320 |
"lstrip": false,
|
321 |
"normalized": true,
|
322 |
"rstrip": false,
|
|
|
324 |
"special": false
|
325 |
},
|
326 |
"50296": {
|
327 |
+
"content": "<PAD>",
|
328 |
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
"rstrip": false,
|
331 |
"single_word": false,
|
332 |
+
"special": true
|
333 |
},
|
334 |
"50297": {
|
335 |
+
"content": "<|end|>",
|
336 |
"lstrip": false,
|
337 |
"normalized": true,
|
338 |
"rstrip": false,
|
|
|
340 |
"special": false
|
341 |
},
|
342 |
"50298": {
|
343 |
+
"content": "<|end_of_turn|>",
|
344 |
"lstrip": false,
|
345 |
"normalized": true,
|
346 |
"rstrip": false,
|
|
|
348 |
"special": false
|
349 |
},
|
350 |
"50299": {
|
351 |
+
"content": "Observation:",
|
352 |
"lstrip": false,
|
353 |
"normalized": true,
|
354 |
"rstrip": false,
|
|
|
356 |
"special": false
|
357 |
},
|
358 |
"50300": {
|
359 |
+
"content": "System:",
|
360 |
"lstrip": false,
|
361 |
"normalized": true,
|
362 |
"rstrip": false,
|
|
|
364 |
"special": false
|
365 |
},
|
366 |
"50301": {
|
367 |
+
"content": "<|function_call|>",
|
368 |
"lstrip": false,
|
369 |
"normalized": true,
|
370 |
"rstrip": false,
|
|
|
372 |
"special": false
|
373 |
},
|
374 |
"50302": {
|
375 |
+
"content": "Azma:",
|
376 |
"lstrip": false,
|
377 |
"normalized": true,
|
378 |
"rstrip": false,
|
|
|
380 |
"special": false
|
381 |
},
|
382 |
"50303": {
|
383 |
+
"content": "Azma",
|
384 |
"lstrip": false,
|
385 |
"normalized": true,
|
386 |
"rstrip": false,
|
|
|
388 |
"special": false
|
389 |
},
|
390 |
"50304": {
|
391 |
+
"content": "<|thoughts|>",
|
392 |
"lstrip": false,
|
393 |
+
"normalized": true,
|
394 |
"rstrip": false,
|
395 |
"single_word": false,
|
396 |
+
"special": false
|
397 |
},
|
398 |
"50305": {
|
399 |
+
"content": "<|response|>",
|
400 |
"lstrip": false,
|
401 |
"normalized": true,
|
402 |
"rstrip": false,
|
|
|
404 |
"special": false
|
405 |
},
|
406 |
"50306": {
|
407 |
+
"content": "User:",
|
408 |
"lstrip": false,
|
409 |
"normalized": true,
|
410 |
"rstrip": false,
|