gpt-tokenizer 2.6.0 → 2.6.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +1 -2
- package/README.md +22 -11
- package/cjs/GptEncoding.d.ts +1 -0
- package/cjs/GptEncoding.js +6 -4
- package/cjs/GptEncoding.js.map +1 -1
- package/cjs/encoding/cl100k_base.d.ts +2 -2
- package/cjs/encoding/cl100k_base.js +3 -2
- package/cjs/encoding/cl100k_base.js.map +1 -1
- package/cjs/encoding/o200k_base.d.ts +2 -2
- package/cjs/encoding/o200k_base.js +3 -2
- package/cjs/encoding/o200k_base.js.map +1 -1
- package/cjs/encoding/p50k_base.d.ts +2 -2
- package/cjs/encoding/p50k_base.js +3 -2
- package/cjs/encoding/p50k_base.js.map +1 -1
- package/cjs/encoding/p50k_edit.d.ts +2 -2
- package/cjs/encoding/p50k_edit.js +3 -2
- package/cjs/encoding/p50k_edit.js.map +1 -1
- package/cjs/encoding/r50k_base.d.ts +2 -2
- package/cjs/encoding/r50k_base.js +3 -2
- package/cjs/encoding/r50k_base.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-0125.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-0125.js +3 -2
- package/cjs/model/gpt-3.5-turbo-0125.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-0301.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-0301.js +3 -2
- package/cjs/model/gpt-3.5-turbo-0301.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-0613.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-0613.js +3 -2
- package/cjs/model/gpt-3.5-turbo-0613.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-1106.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-1106.js +3 -2
- package/cjs/model/gpt-3.5-turbo-1106.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-16k-0613.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-16k-0613.js +3 -2
- package/cjs/model/gpt-3.5-turbo-16k-0613.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-16k.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-16k.js +3 -2
- package/cjs/model/gpt-3.5-turbo-16k.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo-finetune.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo-finetune.js +3 -2
- package/cjs/model/gpt-3.5-turbo-finetune.js.map +1 -1
- package/cjs/model/gpt-3.5-turbo.d.ts +2 -2
- package/cjs/model/gpt-3.5-turbo.js +3 -2
- package/cjs/model/gpt-3.5-turbo.js.map +1 -1
- package/cjs/model/gpt-4-0125-preview.d.ts +2 -2
- package/cjs/model/gpt-4-0125-preview.js +3 -2
- package/cjs/model/gpt-4-0125-preview.js.map +1 -1
- package/cjs/model/gpt-4-0314.d.ts +2 -2
- package/cjs/model/gpt-4-0314.js +3 -2
- package/cjs/model/gpt-4-0314.js.map +1 -1
- package/cjs/model/gpt-4-0613.d.ts +2 -2
- package/cjs/model/gpt-4-0613.js +3 -2
- package/cjs/model/gpt-4-0613.js.map +1 -1
- package/cjs/model/gpt-4-1106-preview.d.ts +2 -2
- package/cjs/model/gpt-4-1106-preview.js +3 -2
- package/cjs/model/gpt-4-1106-preview.js.map +1 -1
- package/cjs/model/gpt-4-1106-vision-preview.d.ts +2 -2
- package/cjs/model/gpt-4-1106-vision-preview.js +3 -2
- package/cjs/model/gpt-4-1106-vision-preview.js.map +1 -1
- package/cjs/model/gpt-4-32k-0314.d.ts +2 -2
- package/cjs/model/gpt-4-32k-0314.js +3 -2
- package/cjs/model/gpt-4-32k-0314.js.map +1 -1
- package/cjs/model/gpt-4-32k-0613.d.ts +2 -2
- package/cjs/model/gpt-4-32k-0613.js +3 -2
- package/cjs/model/gpt-4-32k-0613.js.map +1 -1
- package/cjs/model/gpt-4-32k.d.ts +2 -2
- package/cjs/model/gpt-4-32k.js +3 -2
- package/cjs/model/gpt-4-32k.js.map +1 -1
- package/cjs/model/gpt-4-turbo-2024-04-09.d.ts +2 -2
- package/cjs/model/gpt-4-turbo-2024-04-09.js +3 -2
- package/cjs/model/gpt-4-turbo-2024-04-09.js.map +1 -1
- package/cjs/model/gpt-4-turbo-preview.d.ts +2 -2
- package/cjs/model/gpt-4-turbo-preview.js +3 -2
- package/cjs/model/gpt-4-turbo-preview.js.map +1 -1
- package/cjs/model/gpt-4-turbo.d.ts +2 -2
- package/cjs/model/gpt-4-turbo.js +3 -2
- package/cjs/model/gpt-4-turbo.js.map +1 -1
- package/cjs/model/gpt-4-vision-preview.d.ts +2 -2
- package/cjs/model/gpt-4-vision-preview.js +3 -2
- package/cjs/model/gpt-4-vision-preview.js.map +1 -1
- package/cjs/model/gpt-4.d.ts +2 -2
- package/cjs/model/gpt-4.js +3 -2
- package/cjs/model/gpt-4.js.map +1 -1
- package/cjs/model/gpt-4o-2024-05-13.d.ts +2 -2
- package/cjs/model/gpt-4o-2024-05-13.js +3 -2
- package/cjs/model/gpt-4o-2024-05-13.js.map +1 -1
- package/cjs/model/gpt-4o-2024-08-06-finetune.d.ts +2 -2
- package/cjs/model/gpt-4o-2024-08-06-finetune.js +3 -2
- package/cjs/model/gpt-4o-2024-08-06-finetune.js.map +1 -1
- package/cjs/model/gpt-4o-2024-08-06.d.ts +2 -2
- package/cjs/model/gpt-4o-2024-08-06.js +3 -2
- package/cjs/model/gpt-4o-2024-08-06.js.map +1 -1
- package/cjs/model/gpt-4o-audio-preview-2024-10-01.d.ts +2 -2
- package/cjs/model/gpt-4o-audio-preview-2024-10-01.js +3 -2
- package/cjs/model/gpt-4o-audio-preview-2024-10-01.js.map +1 -1
- package/cjs/model/gpt-4o-audio-preview.d.ts +2 -2
- package/cjs/model/gpt-4o-audio-preview.js +3 -2
- package/cjs/model/gpt-4o-audio-preview.js.map +1 -1
- package/cjs/model/gpt-4o-mini-2024-07-18-finetune.d.ts +2 -2
- package/cjs/model/gpt-4o-mini-2024-07-18-finetune.js +3 -2
- package/cjs/model/gpt-4o-mini-2024-07-18-finetune.js.map +1 -1
- package/cjs/model/gpt-4o-mini-2024-07-18.d.ts +2 -2
- package/cjs/model/gpt-4o-mini-2024-07-18.js +3 -2
- package/cjs/model/gpt-4o-mini-2024-07-18.js.map +1 -1
- package/cjs/model/gpt-4o-mini-training-2024-07-18.d.ts +2 -2
- package/cjs/model/gpt-4o-mini-training-2024-07-18.js +3 -2
- package/cjs/model/gpt-4o-mini-training-2024-07-18.js.map +1 -1
- package/cjs/model/gpt-4o-mini-training.d.ts +2 -2
- package/cjs/model/gpt-4o-mini-training.js +3 -2
- package/cjs/model/gpt-4o-mini-training.js.map +1 -1
- package/cjs/model/gpt-4o-mini.d.ts +2 -2
- package/cjs/model/gpt-4o-mini.js +3 -2
- package/cjs/model/gpt-4o-mini.js.map +1 -1
- package/cjs/model/gpt-4o-realtime-preview-2024-10-01.d.ts +2 -2
- package/cjs/model/gpt-4o-realtime-preview-2024-10-01.js +3 -2
- package/cjs/model/gpt-4o-realtime-preview-2024-10-01.js.map +1 -1
- package/cjs/model/gpt-4o-realtime-preview.d.ts +2 -2
- package/cjs/model/gpt-4o-realtime-preview.js +3 -2
- package/cjs/model/gpt-4o-realtime-preview.js.map +1 -1
- package/cjs/model/gpt-4o.d.ts +2 -2
- package/cjs/model/gpt-4o.js +3 -2
- package/cjs/model/gpt-4o.js.map +1 -1
- package/cjs/modelParams.d.ts +0 -2
- package/cjs/modelParams.js.map +1 -1
- package/cjs/models.d.ts +1 -1
- package/dist/cl100k_base.js +1 -1
- package/dist/cl100k_base.js.map +1 -1
- package/dist/o200k_base.js +1 -1
- package/dist/o200k_base.js.map +1 -1
- package/dist/p50k_base.js +1 -1
- package/dist/p50k_base.js.map +1 -1
- package/dist/p50k_edit.js +1 -1
- package/dist/p50k_edit.js.map +1 -1
- package/dist/r50k_base.js +1 -1
- package/dist/r50k_base.js.map +1 -1
- package/esm/GptEncoding.d.ts +1 -0
- package/esm/GptEncoding.js +6 -4
- package/esm/GptEncoding.js.map +1 -1
- package/esm/codegen/generateJsBpe.js +1 -1
- package/esm/codegen/generateJsBpe.js.map +1 -1
- package/esm/encoding/cl100k_base.d.ts +2 -2
- package/esm/encoding/cl100k_base.js +2 -2
- package/esm/encoding/cl100k_base.js.map +1 -1
- package/esm/encoding/o200k_base.d.ts +2 -2
- package/esm/encoding/o200k_base.js +2 -2
- package/esm/encoding/o200k_base.js.map +1 -1
- package/esm/encoding/p50k_base.d.ts +2 -2
- package/esm/encoding/p50k_base.js +2 -2
- package/esm/encoding/p50k_base.js.map +1 -1
- package/esm/encoding/p50k_edit.d.ts +2 -2
- package/esm/encoding/p50k_edit.js +2 -2
- package/esm/encoding/p50k_edit.js.map +1 -1
- package/esm/encoding/r50k_base.d.ts +2 -2
- package/esm/encoding/r50k_base.js +2 -2
- package/esm/encoding/r50k_base.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-0125.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-0125.js +2 -2
- package/esm/model/gpt-3.5-turbo-0125.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-0301.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-0301.js +2 -2
- package/esm/model/gpt-3.5-turbo-0301.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-0613.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-0613.js +2 -2
- package/esm/model/gpt-3.5-turbo-0613.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-1106.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-1106.js +2 -2
- package/esm/model/gpt-3.5-turbo-1106.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-16k-0613.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-16k-0613.js +2 -2
- package/esm/model/gpt-3.5-turbo-16k-0613.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-16k.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-16k.js +2 -2
- package/esm/model/gpt-3.5-turbo-16k.js.map +1 -1
- package/esm/model/gpt-3.5-turbo-finetune.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo-finetune.js +2 -2
- package/esm/model/gpt-3.5-turbo-finetune.js.map +1 -1
- package/esm/model/gpt-3.5-turbo.d.ts +2 -2
- package/esm/model/gpt-3.5-turbo.js +2 -2
- package/esm/model/gpt-3.5-turbo.js.map +1 -1
- package/esm/model/gpt-4-0125-preview.d.ts +2 -2
- package/esm/model/gpt-4-0125-preview.js +2 -2
- package/esm/model/gpt-4-0125-preview.js.map +1 -1
- package/esm/model/gpt-4-0314.d.ts +2 -2
- package/esm/model/gpt-4-0314.js +2 -2
- package/esm/model/gpt-4-0314.js.map +1 -1
- package/esm/model/gpt-4-0613.d.ts +2 -2
- package/esm/model/gpt-4-0613.js +2 -2
- package/esm/model/gpt-4-0613.js.map +1 -1
- package/esm/model/gpt-4-1106-preview.d.ts +2 -2
- package/esm/model/gpt-4-1106-preview.js +2 -2
- package/esm/model/gpt-4-1106-preview.js.map +1 -1
- package/esm/model/gpt-4-1106-vision-preview.d.ts +2 -2
- package/esm/model/gpt-4-1106-vision-preview.js +2 -2
- package/esm/model/gpt-4-1106-vision-preview.js.map +1 -1
- package/esm/model/gpt-4-32k-0314.d.ts +2 -2
- package/esm/model/gpt-4-32k-0314.js +2 -2
- package/esm/model/gpt-4-32k-0314.js.map +1 -1
- package/esm/model/gpt-4-32k-0613.d.ts +2 -2
- package/esm/model/gpt-4-32k-0613.js +2 -2
- package/esm/model/gpt-4-32k-0613.js.map +1 -1
- package/esm/model/gpt-4-32k.d.ts +2 -2
- package/esm/model/gpt-4-32k.js +2 -2
- package/esm/model/gpt-4-32k.js.map +1 -1
- package/esm/model/gpt-4-turbo-2024-04-09.d.ts +2 -2
- package/esm/model/gpt-4-turbo-2024-04-09.js +2 -2
- package/esm/model/gpt-4-turbo-2024-04-09.js.map +1 -1
- package/esm/model/gpt-4-turbo-preview.d.ts +2 -2
- package/esm/model/gpt-4-turbo-preview.js +2 -2
- package/esm/model/gpt-4-turbo-preview.js.map +1 -1
- package/esm/model/gpt-4-turbo.d.ts +2 -2
- package/esm/model/gpt-4-turbo.js +2 -2
- package/esm/model/gpt-4-turbo.js.map +1 -1
- package/esm/model/gpt-4-vision-preview.d.ts +2 -2
- package/esm/model/gpt-4-vision-preview.js +2 -2
- package/esm/model/gpt-4-vision-preview.js.map +1 -1
- package/esm/model/gpt-4.d.ts +2 -2
- package/esm/model/gpt-4.js +2 -2
- package/esm/model/gpt-4.js.map +1 -1
- package/esm/model/gpt-4o-2024-05-13.d.ts +2 -2
- package/esm/model/gpt-4o-2024-05-13.js +2 -2
- package/esm/model/gpt-4o-2024-05-13.js.map +1 -1
- package/esm/model/gpt-4o-2024-08-06-finetune.d.ts +2 -2
- package/esm/model/gpt-4o-2024-08-06-finetune.js +2 -2
- package/esm/model/gpt-4o-2024-08-06-finetune.js.map +1 -1
- package/esm/model/gpt-4o-2024-08-06.d.ts +2 -2
- package/esm/model/gpt-4o-2024-08-06.js +2 -2
- package/esm/model/gpt-4o-2024-08-06.js.map +1 -1
- package/esm/model/gpt-4o-audio-preview-2024-10-01.d.ts +2 -2
- package/esm/model/gpt-4o-audio-preview-2024-10-01.js +2 -2
- package/esm/model/gpt-4o-audio-preview-2024-10-01.js.map +1 -1
- package/esm/model/gpt-4o-audio-preview.d.ts +2 -2
- package/esm/model/gpt-4o-audio-preview.js +2 -2
- package/esm/model/gpt-4o-audio-preview.js.map +1 -1
- package/esm/model/gpt-4o-mini-2024-07-18-finetune.d.ts +2 -2
- package/esm/model/gpt-4o-mini-2024-07-18-finetune.js +2 -2
- package/esm/model/gpt-4o-mini-2024-07-18-finetune.js.map +1 -1
- package/esm/model/gpt-4o-mini-2024-07-18.d.ts +2 -2
- package/esm/model/gpt-4o-mini-2024-07-18.js +2 -2
- package/esm/model/gpt-4o-mini-2024-07-18.js.map +1 -1
- package/esm/model/gpt-4o-mini-training-2024-07-18.d.ts +2 -2
- package/esm/model/gpt-4o-mini-training-2024-07-18.js +2 -2
- package/esm/model/gpt-4o-mini-training-2024-07-18.js.map +1 -1
- package/esm/model/gpt-4o-mini-training.d.ts +2 -2
- package/esm/model/gpt-4o-mini-training.js +2 -2
- package/esm/model/gpt-4o-mini-training.js.map +1 -1
- package/esm/model/gpt-4o-mini.d.ts +2 -2
- package/esm/model/gpt-4o-mini.js +2 -2
- package/esm/model/gpt-4o-mini.js.map +1 -1
- package/esm/model/gpt-4o-realtime-preview-2024-10-01.d.ts +2 -2
- package/esm/model/gpt-4o-realtime-preview-2024-10-01.js +2 -2
- package/esm/model/gpt-4o-realtime-preview-2024-10-01.js.map +1 -1
- package/esm/model/gpt-4o-realtime-preview.d.ts +2 -2
- package/esm/model/gpt-4o-realtime-preview.js +2 -2
- package/esm/model/gpt-4o-realtime-preview.js.map +1 -1
- package/esm/model/gpt-4o.d.ts +2 -2
- package/esm/model/gpt-4o.js +2 -2
- package/esm/model/gpt-4o.js.map +1 -1
- package/esm/modelParams.d.ts +0 -2
- package/esm/modelParams.js.map +1 -1
- package/esm/models.d.ts +1 -1
- package/package.json +5 -5
- package/src/GptEncoding.ts +9 -6
- package/src/codegen/generateJsBpe.ts +1 -1
- package/src/encoding/cl100k_base.ts +2 -0
- package/src/encoding/o200k_base.ts +2 -0
- package/src/encoding/p50k_base.ts +2 -0
- package/src/encoding/p50k_edit.ts +2 -0
- package/src/encoding/r50k_base.ts +2 -0
- package/src/model/gpt-3.5-turbo-0125.ts +2 -0
- package/src/model/gpt-3.5-turbo-0301.ts +2 -0
- package/src/model/gpt-3.5-turbo-0613.ts +2 -0
- package/src/model/gpt-3.5-turbo-1106.ts +2 -0
- package/src/model/gpt-3.5-turbo-16k-0613.ts +2 -0
- package/src/model/gpt-3.5-turbo-16k.ts +2 -0
- package/src/model/gpt-3.5-turbo-finetune.ts +2 -0
- package/src/model/gpt-3.5-turbo.ts +2 -0
- package/src/model/gpt-4-0125-preview.ts +2 -0
- package/src/model/gpt-4-0314.ts +2 -0
- package/src/model/gpt-4-0613.ts +2 -0
- package/src/model/gpt-4-1106-preview.ts +2 -0
- package/src/model/gpt-4-1106-vision-preview.ts +2 -0
- package/src/model/gpt-4-32k-0314.ts +2 -0
- package/src/model/gpt-4-32k-0613.ts +2 -0
- package/src/model/gpt-4-32k.ts +2 -0
- package/src/model/gpt-4-turbo-2024-04-09.ts +2 -0
- package/src/model/gpt-4-turbo-preview.ts +2 -0
- package/src/model/gpt-4-turbo.ts +2 -0
- package/src/model/gpt-4-vision-preview.ts +2 -0
- package/src/model/gpt-4.ts +2 -0
- package/src/model/gpt-4o-2024-05-13.ts +2 -0
- package/src/model/gpt-4o-2024-08-06-finetune.ts +2 -0
- package/src/model/gpt-4o-2024-08-06.ts +2 -0
- package/src/model/gpt-4o-audio-preview-2024-10-01.ts +2 -0
- package/src/model/gpt-4o-audio-preview.ts +2 -0
- package/src/model/gpt-4o-mini-2024-07-18-finetune.ts +2 -0
- package/src/model/gpt-4o-mini-2024-07-18.ts +2 -0
- package/src/model/gpt-4o-mini-training-2024-07-18.ts +2 -0
- package/src/model/gpt-4o-mini-training.ts +2 -0
- package/src/model/gpt-4o-mini.ts +2 -0
- package/src/model/gpt-4o-realtime-preview-2024-10-01.ts +2 -0
- package/src/model/gpt-4o-realtime-preview.ts +2 -0
- package/src/model/gpt-4o.ts +2 -0
- package/src/modelParams.ts +0 -3
- package/src/models.ts +1 -1
package/LICENSE
CHANGED
|
@@ -1,7 +1,6 @@
|
|
|
1
1
|
MIT License
|
|
2
2
|
|
|
3
|
-
Copyright (c) 2023
|
|
4
|
-
Copyright (c) 2023 Bazyli Brzoska
|
|
3
|
+
Copyright (c) 2023-2024 Bazyli Brzoska
|
|
5
4
|
|
|
6
5
|
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
7
6
|
of this software and associated documentation files (the "Software"), to deal
|
package/README.md
CHANGED
|
@@ -2,14 +2,22 @@
|
|
|
2
2
|
|
|
3
3
|
[](https://codesandbox.io/s/gpt-tokenizer-tjcjoz?fontsize=14&hidenavigation=1&theme=dark)
|
|
4
4
|
|
|
5
|
-
`gpt-tokenizer` is a Token Byte Pair Encoder/Decoder supporting all OpenAI's models (including
|
|
5
|
+
`gpt-tokenizer` is a Token Byte Pair Encoder/Decoder supporting all OpenAI's models (including GPT-3.5, GPT-4, GPT-4o, and o1).
|
|
6
6
|
It's the [_fastest, smallest and lowest footprint_](#benchmarks) GPT tokenizer available for all JavaScript environments. It's written in TypeScript.
|
|
7
7
|
|
|
8
|
-
This
|
|
8
|
+
This library has been trusted by:
|
|
9
9
|
|
|
10
|
-
|
|
10
|
+
- [CodeRabbit](https://www.coderabbit.ai/) (sponsor 🩷)
|
|
11
|
+
- Microsoft ([Teams](https://github.com/microsoft/teams-ai), [GenAIScript](https://github.com/microsoft/genaiscript/))
|
|
12
|
+
- Elastic ([Kibana](https://github.com/elastic/kibana))
|
|
13
|
+
- [Effect TS](https://effect.website/)
|
|
14
|
+
- [Rivet](https://github.com/Ironclad/rivet) by Ironclad
|
|
11
15
|
|
|
12
|
-
|
|
16
|
+
Please consider [🩷 sponsoring](https://github.com/sponsors/niieani) the project if you find it useful.
|
|
17
|
+
|
|
18
|
+
#### Features
|
|
19
|
+
|
|
20
|
+
As of 2023, it is the most feature-complete, open-source GPT tokenizer on NPM. This package is a port of OpenAI's [tiktoken](https://github.com/openai/tiktoken), with some additional, unique features sprinkled on top:
|
|
13
21
|
|
|
14
22
|
- Support for easily tokenizing chats thanks to the `encodeChat` function
|
|
15
23
|
- Support for all current OpenAI models (available encodings: `r50k_base`, `p50k_base`, `p50k_edit`, `cl100k_base` and `o200k_base`)
|
|
@@ -22,10 +30,6 @@ As of 2023, it is the most feature-complete, open-source GPT tokenizer on NPM. I
|
|
|
22
30
|
- Type-safe (written in TypeScript)
|
|
23
31
|
- Works in the browser out-of-the-box
|
|
24
32
|
|
|
25
|
-
Thanks to @dmitry-brazhenko's [SharpToken](https://github.com/dmitry-brazhenko/SharpToken), whose code was served as a reference for the port.
|
|
26
|
-
|
|
27
|
-
Historical note: This package started off as a fork of [latitudegames/GPT-3-Encoder](https://github.com/latitudegames/GPT-3-Encoder), but version 2.0 was rewritten from scratch.
|
|
28
|
-
|
|
29
33
|
## Installation
|
|
30
34
|
|
|
31
35
|
### As NPM package
|
|
@@ -47,7 +51,7 @@ npm install gpt-tokenizer
|
|
|
47
51
|
|
|
48
52
|
If you wish to use a custom encoding, fetch the relevant script.
|
|
49
53
|
|
|
50
|
-
- https://unpkg.com/gpt-tokenizer/dist/o200k_base.js (for `gpt-4o`)
|
|
54
|
+
- https://unpkg.com/gpt-tokenizer/dist/o200k_base.js (for `gpt-4o` and `o1`)
|
|
51
55
|
- https://unpkg.com/gpt-tokenizer/dist/cl100k_base.js (for `gpt-4-*` and `gpt-3.5-turbo`)
|
|
52
56
|
- https://unpkg.com/gpt-tokenizer/dist/p50k_base.js
|
|
53
57
|
- https://unpkg.com/gpt-tokenizer/dist/p50k_edit.js
|
|
@@ -61,7 +65,7 @@ Refer to [supported models and their encodings](#Supported-models-and-their-enco
|
|
|
61
65
|
|
|
62
66
|
The playground is published under a memorable URL: https://gpt-tokenizer.dev/
|
|
63
67
|
|
|
64
|
-
You can play with the package in the browser using the [Playground](https://codesandbox.io/s/gpt-tokenizer-tjcjoz?fontsize=14&hidenavigation=1&theme=dark).
|
|
68
|
+
You can play with the package in the browser using the CodeSandbox [Playground](https://codesandbox.io/s/gpt-tokenizer-tjcjoz?fontsize=14&hidenavigation=1&theme=dark).
|
|
65
69
|
|
|
66
70
|
[](https://codesandbox.io/s/gpt-tokenizer-tjcjoz?fontsize=14&hidenavigation=1&theme=dark)
|
|
67
71
|
|
|
@@ -69,6 +73,8 @@ The playground mimics the official [OpenAI Tokenizer](https://platform.openai.co
|
|
|
69
73
|
|
|
70
74
|
## Usage
|
|
71
75
|
|
|
76
|
+
The library provides various functions to transform text into (and from) a sequence of integers (tokens) that can be fed into an LLM model. The transformation is done using a Byte Pair Encoding (BPE) algorithm used by OpenAI.
|
|
77
|
+
|
|
72
78
|
```typescript
|
|
73
79
|
import {
|
|
74
80
|
encode,
|
|
@@ -176,13 +182,14 @@ import {
|
|
|
176
182
|
|
|
177
183
|
### Supported models and their encodings
|
|
178
184
|
|
|
185
|
+
- `o1-*` (`o200k_base`)
|
|
179
186
|
- `gpt-4o` (`o200k_base`)
|
|
180
187
|
- `gpt-4-*` (`cl100k_base`)
|
|
181
188
|
- `gpt-3.5-turbo` (`cl100k_base`)
|
|
182
189
|
- `text-davinci-003` (`p50k_base`)
|
|
183
190
|
- `text-davinci-002` (`p50k_base`)
|
|
184
191
|
- `text-davinci-001` (`r50k_base`)
|
|
185
|
-
- ...and many other models, see [
|
|
192
|
+
- ...and many other models, see [models.ts](./src/models.ts) for an up-to-date list of supported models and their encodings.
|
|
186
193
|
|
|
187
194
|
Note: if you're using `gpt-3.5-*` or `gpt-4-*` and don't see the model you're looking for, use the `cl100k_base` encoding directly.
|
|
188
195
|
|
|
@@ -381,4 +388,8 @@ MIT
|
|
|
381
388
|
|
|
382
389
|
Contributions are welcome! Please open a pull request or an issue to discuss your bug reports, or use the discussions feature for ideas or any other inquiries.
|
|
383
390
|
|
|
391
|
+
## Thanks
|
|
392
|
+
|
|
393
|
+
Thanks to @dmitry-brazhenko's [SharpToken](https://github.com/dmitry-brazhenko/SharpToken), whose code was served as a reference for the port.
|
|
394
|
+
|
|
384
395
|
Hope you find the `gpt-tokenizer` useful in your projects!
|
package/cjs/GptEncoding.d.ts
CHANGED
|
@@ -25,6 +25,7 @@ export declare class GptEncoding {
|
|
|
25
25
|
private specialTokensSet;
|
|
26
26
|
private allSpecialTokenRegex;
|
|
27
27
|
private defaultSpecialTokenConfig;
|
|
28
|
+
readonly vocabularySize: number;
|
|
28
29
|
private constructor();
|
|
29
30
|
static getEncodingApi(encodingName: EncodingName, getMergeableRanks: GetMergeableRanksFn): GptEncoding;
|
|
30
31
|
static getEncodingApiForModel(modelName: ModelName, getMergeableRanks: GetMergeableRanksFn): GptEncoding;
|
package/cjs/GptEncoding.js
CHANGED
|
@@ -22,6 +22,7 @@ class GptEncoding {
|
|
|
22
22
|
specialTokensSet;
|
|
23
23
|
allSpecialTokenRegex;
|
|
24
24
|
defaultSpecialTokenConfig;
|
|
25
|
+
vocabularySize;
|
|
25
26
|
constructor({ mergeableBytePairRanks, specialTokenMapping, expectedVocabularySize, modelName, ...rest }) {
|
|
26
27
|
this.specialTokenMapping = specialTokenMapping;
|
|
27
28
|
this.specialTokensSet = new Set(this.specialTokenMapping.keys());
|
|
@@ -33,11 +34,12 @@ class GptEncoding {
|
|
|
33
34
|
});
|
|
34
35
|
this.defaultSpecialTokenConfig = this.processSpecialTokens();
|
|
35
36
|
const maxTokenValue = Math.max(mergeableBytePairRanks.length - 1, (0, util_js_1.getMaxValueFromMap)(specialTokenMapping));
|
|
37
|
+
this.vocabularySize =
|
|
38
|
+
this.bytePairEncodingCoreProcessor.mergeableBytePairRankCount +
|
|
39
|
+
specialTokenMapping.size;
|
|
36
40
|
if (expectedVocabularySize !== undefined) {
|
|
37
|
-
if (this.
|
|
38
|
-
|
|
39
|
-
expectedVocabularySize) {
|
|
40
|
-
throw new Error('The number of mergeable tokens and special tokens must be equal to explicit_n_vocab.');
|
|
41
|
+
if (this.vocabularySize !== expectedVocabularySize) {
|
|
42
|
+
throw new Error('The number of mergeable tokens and special tokens must be equal to expectedVocabularySize.');
|
|
41
43
|
}
|
|
42
44
|
if (maxTokenValue !== expectedVocabularySize - 1) {
|
|
43
45
|
throw new Error(`The model encodings are invalid. The maximum token value must be equal to expectedVocabularySize - 1. Currently ${maxTokenValue}, expected ${expectedVocabularySize - 1}`);
|
package/cjs/GptEncoding.js.map
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"GptEncoding.js","sourceRoot":"","sources":["../src/GptEncoding.ts"],"names":[],"mappings":";;;AAAA,uDAAuD;AACvD,sCAAsC;AACtC,uEAAyE;AACzE,6CAOqB;AACrB,qDAMyB;AACzB,yDAS2B;AAC3B,6CAAiE;AACjE,uCAAoE;AAEvD,QAAA,kBAAkB,GAAG,KAAK,CAAA;AAsBvC,MAAa,WAAW;IACtB,MAAM,CAAC,WAAW,GAAG,8BAAW,CAAA;IAChC,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAE5B,SAAS,CAAY;IACb,6BAA6B,CAAsB;IACnD,mBAAmB,CAAqB;IACxC,gBAAgB,CAAa;IAC7B,oBAAoB,CAAQ;IAC5B,yBAAyB,CAAoB;
|
|
1
|
+
{"version":3,"file":"GptEncoding.js","sourceRoot":"","sources":["../src/GptEncoding.ts"],"names":[],"mappings":";;;AAAA,uDAAuD;AACvD,sCAAsC;AACtC,uEAAyE;AACzE,6CAOqB;AACrB,qDAMyB;AACzB,yDAS2B;AAC3B,6CAAiE;AACjE,uCAAoE;AAEvD,QAAA,kBAAkB,GAAG,KAAK,CAAA;AAsBvC,MAAa,WAAW;IACtB,MAAM,CAAC,WAAW,GAAG,8BAAW,CAAA;IAChC,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAC5B,MAAM,CAAC,SAAS,GAAG,4BAAS,CAAA;IAE5B,SAAS,CAAY;IACb,6BAA6B,CAAsB;IACnD,mBAAmB,CAAqB;IACxC,gBAAgB,CAAa;IAC7B,oBAAoB,CAAQ;IAC5B,yBAAyB,CAAoB;IAE5C,cAAc,CAAQ;IAE/B,YAAoB,EAClB,sBAAsB,EACtB,mBAAmB,EACnB,sBAAsB,EACtB,SAAS,EACT,GAAG,IAAI,EACQ;QACf,IAAI,CAAC,mBAAmB,GAAG,mBAAmB,CAAA;QAC9C,IAAI,CAAC,gBAAgB,GAAG,IAAI,GAAG,CAAS,IAAI,CAAC,mBAAmB,CAAC,IAAI,EAAE,CAAC,CAAA;QACxE,IAAI,CAAC,oBAAoB,GAAG,IAAA,8BAAoB,EAAC,IAAI,CAAC,gBAAgB,CAAC,CAAA;QAEvE,IAAI,CAAC,6BAA6B,GAAG,IAAI,8CAAoB,CAAC;YAC5D,sBAAsB;YACtB,mBAAmB;YACnB,GAAG,IAAI;SACR,CAAC,CAAA;QACF,IAAI,CAAC,yBAAyB,GAAG,IAAI,CAAC,oBAAoB,EAAE,CAAA;QAE5D,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,CAC5B,sBAAsB,CAAC,MAAM,GAAG,CAAC,EACjC,IAAA,4BAAkB,EAAC,mBAAmB,CAAC,CACxC,CAAA;QAED,IAAI,CAAC,cAAc;YACjB,IAAI,CAAC,6BAA6B,CAAC,0BAA0B;gBAC7D,mBAAmB,CAAC,IAAI,CAAA;QAE1B,IAAI,sBAAsB,KAAK,SAAS,EAAE,CAAC;YACzC,IAAI,IAAI,CAAC,cAAc,KAAK,sBAAsB,EAAE,CAAC;gBACnD,MAAM,IAAI,KAAK,CACb,4FAA4F,CAC7F,CAAA;YACH,CAAC;YAED,IAAI,aAAa,KAAK,sBAAsB,GAAG,CAAC,EAAE,CAAC;gBACjD,MAAM,IAAI,KAAK,CACb,mHAAmH,aAAa,cAC9H,sBAAsB,GAAG,CAC3B,EAAE,CACH,CAAA;YACH,CAAC;QACH,CAAC;QAED,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACpC,IAAI,CAAC,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACpC,IAAI,CAAC,eAAe,GAAG,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACtD,IAAI,CAAC,eAAe,GAAG,IAAI,CAAC,eAAe,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QACtD,IAAI,CAAC,oBAAoB,GAAG,IAAI,CAAC,oBAAoB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAChE,IAAI,CAAC,WAAW,GAAG,IAAI,CAAC,WAAW,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC9C,IAAI,CAAC,kBAAkB,GAAG,IAAI,CAAC,kBAAkB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC5D,IAAI,CAAC,UAAU,GAAG,IAAI,CAAC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC5C,IAAI,CAAC,mBAAmB,GAAG,IAAI,CAAC,mBAAmB,CAAC,IAAI,CAAC,IAAI,CAAC,CAAA;QAC9D,IAAI,CAAC,SAAS,GAAG,SAAS,CAAA;IAC5B,CAAC;IAED,MAAM,CAAC,cAAc,CACnB,YAA0B,EAC1B,iBAAsC;QAEtC,MAAM,WAAW,GAAG,IAAA,kCAAiB,EAAC,YAAY,EAAE,iBAAiB,CAAC,CAAA;QACtE,OAAO,IAAI,WAAW,CAAC,WAAW,CAAC,CAAA;IACrC,CAAC;IAED,MAAM,CAAC,sBAAsB,CAC3B,SAAoB,EACpB,iBAAsC;QAEtC,MAAM,YAAY,GAAG,+BAAkB,CAAC,SAAS,CAAC,CAAA;QAClD,MAAM,WAAW,GAAG,IAAA,kCAAiB,EAAC,YAAY,EAAE,iBAAiB,CAAC,CAAA;QACtE,OAAO,IAAI,WAAW,CAAC,EAAE,GAAG,WAAW,EAAE,SAAS,EAAE,CAAC,CAAA;IACvD,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,mBAAmB,CAC9B,YAA0B,EAC1B,iBAA2C;QAE3C,MAAM,WAAW,GAAG,MAAM,IAAA,oCAAmB,EAC3C,YAAY,EACZ,iBAAiB,CAClB,CAAA;QACD,OAAO,IAAI,WAAW,CAAC,WAAW,CAAC,CAAA;IACrC,CAAC;IAED,MAAM,CAAC,KAAK,CAAC,2BAA2B,CACtC,SAAoB,EACpB,iBAA2C;QAE3C,MAAM,YAAY,GAAG,+BAAkB,CAAC,SAAS,CAAC,CAAA;QAClD,MAAM,WAAW,GAAG,MAAM,IAAA,oCAAmB,EAC3C,YAAY,EACZ,iBAAiB,CAClB,CAAA;QACD,OAAO,IAAI,WAAW,CAAC,EAAE,GAAG,WAAW,EAAE,SAAS,EAAE,CAAC,CAAA;IACvD,CAAC;IAEO,oBAAoB,CAAC,EAC3B,cAAc,EACd,iBAAiB,MACA,EAAE;QACnB,IAAI,YAAgC,CAAA;QAEpC,IAAI,cAAc,EAAE,GAAG,CAAC,0BAAkB,CAAC,EAAE,CAAC;YAC5C,cAAc,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAA;QACjD,CAAC;QAED,IAAI,CAAC,iBAAiB,IAAI,iBAAiB,CAAC,GAAG,CAAC,0BAAkB,CAAC,EAAE,CAAC;YACpE,gDAAgD;YAChD,iBAAiB,GAAG,IAAI,GAAG,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAA;YAClD,IAAI,cAAc,EAAE,IAAI,EAAE,CAAC;gBACzB,cAAc,CAAC,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,iBAAkB,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;gBAC/D,iBAAiB,CAAC,OAAO,CAAC,CAAC,GAAG,EAAE,EAAE,CAAC,cAAc,CAAC,MAAM,CAAC,GAAG,CAAC,CAAC,CAAA;gBAC9D,YAAY,GAAG,IAAA,8BAAoB,EAAC,iBAAiB,CAAC,CAAA;YACxD,CAAC;iBAAM,CAAC;gBACN,YAAY,GAAG,IAAI,CAAC,oBAAoB,CAAA;YAC1C,CAAC;QACH,CAAC;QAED,OAAO,EAAE,cAAc,EAAE,YAAY,EAAE,CAAA;IACzC,CAAC;IAED,eAAe,CACb,YAAoB,EACpB,aAA6B;QAE7B,MAAM,kBAAkB,GAAG,aAAa;YACtC,CAAC,CAAC,IAAI,CAAC,oBAAoB,CAAC,aAAa,CAAC;YAC1C,CAAC,CAAC,IAAI,CAAC,yBAAyB,CAAA;QAElC,IAAI,kBAAkB,CAAC,YAAY,EAAE,CAAC;YACpC,MAAM,KAAK,GAAG,YAAY,CAAC,KAAK,CAAC,kBAAkB,CAAC,YAAY,CAAC,CAAA;YACjE,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CAAC,mCAAmC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;YAChE,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC,6BAA6B,CAAC,qBAAqB,CAC7D,YAAY,EACZ,kBAAkB,CAAC,cAAc,CAClC,CAAA;IACH,CAAC;IAED,MAAM,CAAC,YAAoB,EAAE,aAA6B;QACxD,MAAM,kBAAkB,GAAG,aAAa;YACtC,CAAC,CAAC,IAAI,CAAC,oBAAoB,CAAC,aAAa,CAAC;YAC1C,CAAC,CAAC,IAAI,CAAC,yBAAyB,CAAA;QAElC,IAAI,kBAAkB,CAAC,YAAY,EAAE,CAAC;YACpC,MAAM,KAAK,GAAG,YAAY,CAAC,KAAK,CAAC,kBAAkB,CAAC,YAAY,CAAC,CAAA;YACjE,IAAI,KAAK,KAAK,IAAI,EAAE,CAAC;gBACnB,MAAM,IAAI,KAAK,CAAC,mCAAmC,KAAK,CAAC,CAAC,CAAC,EAAE,CAAC,CAAA;YAChE,CAAC;QACH,CAAC;QAED,OAAO,IAAI,CAAC,6BAA6B,CAAC,YAAY,CACpD,YAAY,EACZ,kBAAkB,CAAC,cAAc,CAClC,CAAA;IACH,CAAC;IAED;;;;;;OAMG;IACH,CAAC,mBAAmB,CAClB,IAA2B,EAC3B,KAAK,GAAG,IAAI,CAAC,SAAS;QAEtB,IAAI,CAAC,KAAK,EAAE,CAAC;YACX,MAAM,IAAI,KAAK,CACb,sFAAsF,CACvF,CAAA;QACH,CAAC;QAED,MAAM,MAAM,GACV,4BAAe,CAAC,KAAsB,CAAC,CAAA;QACzC,MAAM,cAAc,GAAG,IAAI,CAAC,mBAAmB,CAAC,GAAG,CAAC,0BAAO,CAAC,CAAA;QAC5D,MAAM,YAAY,GAAG,IAAI,CAAC,mBAAmB,CAAC,GAAG,CAAC,wBAAK,CAAC,CAAA;QAExD,IAAI,CAAC,MAAM,IAAI,cAAc,KAAK,SAAS,IAAI,YAAY,KAAK,SAAS,EAAE,CAAC;YAC1E,MAAM,IAAI,KAAK,CAAC,UAAU,KAAK,0BAA0B,CAAC,CAAA;QAC5D,CAAC;QACD,MAAM,cAAc,GAAG,IAAI,GAAG,CAAC,CAAC,wBAAK,CAAC,CAAC,CAAA;QACvC,MAAM,EAAE,gBAAgB,EAAE,aAAa,EAAE,GAAG,MAAM,CAAA;QAClD,MAAM,uBAAuB,GAC3B,gBAAgB,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,gBAAgB,CAAC,CAAC,CAAC,CAAC,EAAE,CAAA;QAClE,MAAM,oBAAoB,GACxB,aAAa,CAAC,MAAM,GAAG,CAAC;YACtB,CAAC,CAAC,IAAI,CAAC,MAAM,CAAC,aAAa,EAAE,EAAE,cAAc,EAAE,CAAC;YAChD,CAAC,CAAC,EAAE,CAAA;QACR,MAAM,SAAS,GAAG,IAAI,GAAG,EAAoB,CAAA;QAE7C,KAAK,MAAM,EAAE,IAAI,GAAG,QAAQ,EAAE,IAAI,GAAG,IAAI,EAAE,OAAO,EAAE,IAAI,IAAI,EAAE,CAAC;YAC7D,IAAI,OAAO,KAAK,SAAS,EAAE,CAAC;gBAC1B,MAAM,IAAI,KAAK,CAAC,2CAA2C,CAAC,CAAA;YAC9D,CAAC;YAED,MAAM,CAAC,cAAc,CAAC,CAAA;YACtB,MAAM,WAAW,GAAG,SAAS,CAAC,GAAG,CAAC,IAAI,CAAC,IAAI,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAA;YAC5D,SAAS,CAAC,GAAG,CAAC,IAAI,EAAE,WAAW,CAAC,CAAA;YAChC,MAAM,WAAW,CAAA;YACjB,IAAI,oBAAoB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;gBACpC,MAAM,oBAAoB,CAAA;YAC5B,CAAC;YACD,KAAK,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,OAAO,CAAC,CAAA;YACpC,MAAM,CAAC,YAAY,CAAC,CAAA;YACpB,MAAM,uBAAuB,CAAA;QAC/B,CAAC;QAED,2DAA2D;QAC3D,MAAM,CAAC,cAAc,CAAC,CAAA;QACtB,KAAK,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,WAAW,CAAC,CAAA;QACxC,IAAI,oBAAoB,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACpC,MAAM,oBAAoB,CAAA;QAC5B,CAAC;IACH,CAAC;IAED;;;;;;OAMG;IACH,UAAU,CAAC,IAA4B,EAAE,KAAK,GAAG,IAAI,CAAC,SAAS;QAC7D,OAAO,CAAC,GAAG,IAAI,CAAC,mBAAmB,CAAC,IAAI,EAAE,KAAK,CAAC,CAAC,CAAC,IAAI,EAAE,CAAA;IAC1D,CAAC;IAED;;OAEG;IACH,kBAAkB,CAChB,KAAqC,EACrC,UAAkB;QAElB,MAAM,cAAc,GAClB,OAAO,KAAK,KAAK,QAAQ;YACvB,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,KAAK,CAAC;YAC7B,CAAC,CAAC,IAAI,CAAC,mBAAmB,CAAC,KAAK,CAAC,CAAA;QACrC,IAAI,KAAK,GAAG,CAAC,CAAA;QACb,KAAK,MAAM,MAAM,IAAI,cAAc,EAAE,CAAC;YACpC,KAAK,IAAI,MAAM,CAAC,MAAM,CAAA;YACtB,IAAI,KAAK,GAAG,UAAU,EAAE,CAAC;gBACvB,OAAO,KAAK,CAAA;YACd,CAAC;QACH,CAAC;QACD,OAAO,KAAK,CAAA;IACd,CAAC;IAED,MAAM,CAAC,mBAAqC;QAC1C,OAAO,IAAI,CAAC,6BAA6B,CAAC,YAAY,CAAC,mBAAmB,CAAC,CAAA;IAC7E,CAAC;IAED,CAAC,eAAe,CACd,mBAAqC;QAErC,MAAM,oBAAoB,GACxB,IAAI,CAAC,6BAA6B,CAAC,qBAAqB,CACtD,mBAAmB,CACpB,CAAA;QAEH,IAAI,MAAM,GAAG,EAAE,CAAA;QAEf,KAAK,MAAM,WAAW,IAAI,oBAAoB,EAAE,CAAC;YAC/C,MAAM;gBACJ,OAAO,WAAW,KAAK,QAAQ;oBAC7B,CAAC,CAAC,WAAW;oBACb,CAAC,CAAC,iCAAO,CAAC,MAAM,CAAC,WAAW,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAA;YAEnD,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,IAAI,IAAA,+CAAkC,EAAC,MAAM,CAAC,EAAE,CAAC;gBACtE,yEAAyE;gBACzE,uCAAuC;gBACvC,SAAQ;YACV,CAAC;iBAAM,CAAC;gBACN,MAAM,MAAM,CAAA;gBACZ,eAAe;gBACf,MAAM,GAAG,EAAE,CAAA;YACb,CAAC;QACH,CAAC;QAED,+CAA+C;QAC/C,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACtB,MAAM,MAAM,CAAA;QACd,CAAC;IACH,CAAC;IAED,KAAK,CAAC,CAAC,oBAAoB,CACzB,mBAA0C;QAE1C,MAAM,oBAAoB,GACxB,IAAI,CAAC,6BAA6B,CAAC,yBAAyB,CAC1D,mBAAmB,CACpB,CAAA;QAEH,IAAI,MAAM,GAAG,EAAE,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,WAAW,IAAI,oBAAoB,EAAE,CAAC;YACrD,MAAM;gBACJ,OAAO,WAAW,KAAK,QAAQ;oBAC7B,CAAC,CAAC,WAAW;oBACb,CAAC,CAAC,iCAAO,CAAC,MAAM,CAAC,WAAW,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAA;YAEnD,IAAI,MAAM,CAAC,MAAM,KAAK,CAAC,IAAI,IAAA,+CAAkC,EAAC,MAAM,CAAC,EAAE,CAAC;gBACtE,yEAAyE;gBACzE,uCAAuC;gBACvC,SAAQ;YACV,CAAC;iBAAM,CAAC;gBACN,MAAM,MAAM,CAAA;gBACZ,eAAe;gBACf,MAAM,GAAG,EAAE,CAAA;YACb,CAAC;QACH,CAAC;QAED,+CAA+C;QAC/C,IAAI,MAAM,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;YACtB,MAAM,MAAM,CAAA;QACd,CAAC;IACH,CAAC;IAED,KAAK,CAAC,WAAW,CACf,mBAA0C;QAE1C,MAAM,oBAAoB,GACxB,IAAI,CAAC,6BAA6B,CAAC,yBAAyB,CAC1D,mBAAmB,CACpB,CAAA;QAEH,IAAI,MAAM,GAAG,EAAE,CAAA;QAEf,IAAI,KAAK,EAAE,MAAM,WAAW,IAAI,oBAAoB,EAAE,CAAC;YACrD,MAAM;gBACJ,OAAO,WAAW,KAAK,QAAQ;oBAC7B,CAAC,CAAC,WAAW;oBACb,CAAC,CAAC,iCAAO,CAAC,MAAM,CAAC,WAAW,EAAE,EAAE,MAAM,EAAE,IAAI,EAAE,CAAC,CAAA;QACrD,CAAC;QAED,OAAO,MAAM,CAAA;IACf,CAAC;;AAnWH,kCAoWC"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined>, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,13 +17,13 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const cl100k_base_js_1 = __importDefault(require("../bpeRanks/cl100k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApi('cl100k_base', () => cl100k_base_js_1.default);
|
|
26
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, } = api;
|
|
26
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, vocabularySize, } = api;
|
|
27
27
|
exports.decode = decode;
|
|
28
28
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
29
29
|
exports.decodeGenerator = decodeGenerator;
|
|
@@ -32,6 +32,7 @@ exports.encodeGenerator = encodeGenerator;
|
|
|
32
32
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
33
33
|
exports.encodeChat = encodeChat;
|
|
34
34
|
exports.encodeChatGenerator = encodeChatGenerator;
|
|
35
|
+
exports.vocabularySize = vocabularySize;
|
|
35
36
|
// eslint-disable-next-line import/no-default-export
|
|
36
37
|
exports.default = api;
|
|
37
38
|
//# sourceMappingURL=cl100k_base.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"cl100k_base.js","sourceRoot":"","sources":["../../src/encoding/cl100k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,aAAa,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACrE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,
|
|
1
|
+
{"version":3,"file":"cl100k_base.js","sourceRoot":"","sources":["../../src/encoding/cl100k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,aAAa,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACrE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,EACnB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AAGN,0CAAe;AACf,gDAAkB;AAHlB,gCAAU;AACV,kDAAmB;AAGnB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined>, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,13 +17,13 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const o200k_base_js_1 = __importDefault(require("../bpeRanks/o200k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApi('o200k_base', () => o200k_base_js_1.default);
|
|
26
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, } = api;
|
|
26
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, vocabularySize, } = api;
|
|
27
27
|
exports.decode = decode;
|
|
28
28
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
29
29
|
exports.decodeGenerator = decodeGenerator;
|
|
@@ -32,6 +32,7 @@ exports.encodeGenerator = encodeGenerator;
|
|
|
32
32
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
33
33
|
exports.encodeChat = encodeChat;
|
|
34
34
|
exports.encodeChatGenerator = encodeChatGenerator;
|
|
35
|
+
exports.vocabularySize = vocabularySize;
|
|
35
36
|
// eslint-disable-next-line import/no-default-export
|
|
36
37
|
exports.default = api;
|
|
37
38
|
//# sourceMappingURL=o200k_base.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"o200k_base.js","sourceRoot":"","sources":["../../src/encoding/o200k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,8EAAgD;AAChD,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,YAAY,EAAE,GAAG,EAAE,CAAC,uBAAQ,CAAC,CAAA;AACpE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,
|
|
1
|
+
{"version":3,"file":"o200k_base.js","sourceRoot":"","sources":["../../src/encoding/o200k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,8EAAgD;AAChD,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,YAAY,EAAE,GAAG,EAAE,CAAC,uBAAQ,CAAC,CAAA;AACpE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,EACnB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AAGN,0CAAe;AACf,gDAAkB;AAHlB,gCAAU;AACV,kDAAmB;AAGnB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number;
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,19 +17,20 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const p50k_base_js_1 = __importDefault(require("../bpeRanks/p50k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApi('p50k_base', () => p50k_base_js_1.default);
|
|
26
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, } = api;
|
|
26
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, } = api;
|
|
27
27
|
exports.decode = decode;
|
|
28
28
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
29
29
|
exports.decodeGenerator = decodeGenerator;
|
|
30
30
|
exports.encode = encode;
|
|
31
31
|
exports.encodeGenerator = encodeGenerator;
|
|
32
32
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
33
|
+
exports.vocabularySize = vocabularySize;
|
|
33
34
|
// eslint-disable-next-line import/no-default-export
|
|
34
35
|
exports.default = api;
|
|
35
36
|
//# sourceMappingURL=p50k_base.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"p50k_base.js","sourceRoot":"","sources":["../../src/encoding/p50k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,
|
|
1
|
+
{"version":3,"file":"p50k_base.js","sourceRoot":"","sources":["../../src/encoding/p50k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AACN,0CAAe;AACf,gDAAkB;AAClB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number;
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,19 +17,20 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const p50k_base_js_1 = __importDefault(require("../bpeRanks/p50k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApi('p50k_edit', () => p50k_base_js_1.default);
|
|
26
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, } = api;
|
|
26
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, } = api;
|
|
27
27
|
exports.decode = decode;
|
|
28
28
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
29
29
|
exports.decodeGenerator = decodeGenerator;
|
|
30
30
|
exports.encode = encode;
|
|
31
31
|
exports.encodeGenerator = encodeGenerator;
|
|
32
32
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
33
|
+
exports.vocabularySize = vocabularySize;
|
|
33
34
|
// eslint-disable-next-line import/no-default-export
|
|
34
35
|
exports.default = api;
|
|
35
36
|
//# sourceMappingURL=p50k_edit.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"p50k_edit.js","sourceRoot":"","sources":["../../src/encoding/p50k_edit.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,
|
|
1
|
+
{"version":3,"file":"p50k_edit.js","sourceRoot":"","sources":["../../src/encoding/p50k_edit.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AACN,0CAAe;AACf,gDAAkB;AAClB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number;
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,19 +17,20 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const r50k_base_js_1 = __importDefault(require("../bpeRanks/r50k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApi('r50k_base', () => r50k_base_js_1.default);
|
|
26
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, } = api;
|
|
26
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, vocabularySize, } = api;
|
|
27
27
|
exports.decode = decode;
|
|
28
28
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
29
29
|
exports.decodeGenerator = decodeGenerator;
|
|
30
30
|
exports.encode = encode;
|
|
31
31
|
exports.encodeGenerator = encodeGenerator;
|
|
32
32
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
33
|
+
exports.vocabularySize = vocabularySize;
|
|
33
34
|
// eslint-disable-next-line import/no-default-export
|
|
34
35
|
exports.default = api;
|
|
35
36
|
//# sourceMappingURL=r50k_base.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"r50k_base.js","sourceRoot":"","sources":["../../src/encoding/r50k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,
|
|
1
|
+
{"version":3,"file":"r50k_base.js","sourceRoot":"","sources":["../../src/encoding/r50k_base.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,4EAA+C;AAC/C,sDAA+C;AAE/C,sDAAmC;AAEnC,MAAM,GAAG,GAAG,4BAAW,CAAC,cAAc,CAAC,WAAW,EAAE,GAAG,EAAE,CAAC,sBAAQ,CAAC,CAAA;AACnE,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AACN,0CAAe;AACf,gDAAkB;AAClB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined>, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,14 +17,14 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const cl100k_base_js_1 = __importDefault(require("../bpeRanks/cl100k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
// prettier-ignore
|
|
26
26
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApiForModel('gpt-3.5-turbo-0125', () => cl100k_base_js_1.default);
|
|
27
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, } = api;
|
|
27
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, vocabularySize, } = api;
|
|
28
28
|
exports.decode = decode;
|
|
29
29
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
30
30
|
exports.decodeGenerator = decodeGenerator;
|
|
@@ -33,6 +33,7 @@ exports.encodeGenerator = encodeGenerator;
|
|
|
33
33
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
34
34
|
exports.encodeChat = encodeChat;
|
|
35
35
|
exports.encodeChatGenerator = encodeChatGenerator;
|
|
36
|
+
exports.vocabularySize = vocabularySize;
|
|
36
37
|
// eslint-disable-next-line import/no-default-export
|
|
37
38
|
exports.default = api;
|
|
38
39
|
//# sourceMappingURL=gpt-3.5-turbo-0125.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"gpt-3.5-turbo-0125.js","sourceRoot":"","sources":["../../src/model/gpt-3.5-turbo-0125.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AACnC,kBAAkB;AAClB,MAAM,GAAG,GAAG,4BAAW,CAAC,sBAAsB,CAAC,oBAAoB,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACpF,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,
|
|
1
|
+
{"version":3,"file":"gpt-3.5-turbo-0125.js","sourceRoot":"","sources":["../../src/model/gpt-3.5-turbo-0125.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AACnC,kBAAkB;AAClB,MAAM,GAAG,GAAG,4BAAW,CAAC,sBAAsB,CAAC,oBAAoB,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACpF,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,EACnB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AAGN,0CAAe;AACf,gDAAkB;AAHlB,gCAAU;AACV,kDAAmB;AAGnB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import { GptEncoding } from '../GptEncoding.js';
|
|
2
2
|
export * from '../specialTokens.js';
|
|
3
3
|
declare const api: GptEncoding;
|
|
4
|
-
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined
|
|
5
|
-
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, };
|
|
4
|
+
declare const decode: (inputTokensToDecode: Iterable<number>) => string, decodeAsyncGenerator: (inputTokensToDecode: AsyncIterable<number>) => AsyncGenerator<string, void>, decodeGenerator: (inputTokensToDecode: Iterable<number>) => Generator<string, void, void>, encode: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => number[], encodeGenerator: (lineToEncode: string, encodeOptions?: import("../GptEncoding.js").EncodeOptions) => Generator<number[], number, undefined>, isWithinTokenLimit: (input: string | Iterable<import("../GptEncoding.js").ChatMessage>, tokenLimit: number) => false | number, encodeChat: (chat: readonly import("../GptEncoding.js").ChatMessage[], model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => number[], encodeChatGenerator: (chat: Iterable<import("../GptEncoding.js").ChatMessage>, model?: "gpt-4o" | "gpt-3.5-turbo" | "gpt-3.5-turbo-instruct" | "babbage-002" | "davinci-002" | "text-embedding-3-small" | "o1-preview" | "o1-preview-2024-09-12" | "o1-mini" | "o1-mini-2024-09-12" | "chatgpt-4o-latest" | "gpt-4o-2024-08-06" | "gpt-4o-2024-05-13" | "gpt-4o-mini" | "gpt-4o-mini-2024-07-18" | "gpt-4o-realtime-preview" | "gpt-4o-realtime-preview-2024-10-01" | "gpt-4o-audio-preview" | "gpt-4o-audio-preview-2024-10-01" | "gpt-4o-2024-08-06-finetune" | "gpt-4o-mini-2024-07-18-finetune" | "gpt-4o-mini-training" | "gpt-4o-mini-training-2024-07-18" | "gpt-4-turbo" | "gpt-4-turbo-2024-04-09" | "gpt-4-turbo-preview" | "gpt-4-0125-preview" | "gpt-4-1106-preview" | "gpt-4" | "gpt-4-0613" | "gpt-3.5-turbo-0125" | "gpt-3.5-turbo-1106" | "gpt-3.5-turbo-finetune" | "gpt-3.5-turbo-16k" | "gpt-4-32k" | "gpt-4-32k-0613" | "gpt-4-vision-preview" | "gpt-4-1106-vision-preview" | "gpt-4-0314" | "gpt-4-32k-0314" | "gpt-3.5-turbo-0613" | "gpt-3.5-turbo-16k-0613" | "gpt-3.5-turbo-0301" | "text-embedding-3-large" | "text-embedding-ada-002" | "gpt-3.5-turbo-instruct-0914" | "text-ada-001" | "text-babbage-001" | "text-curie-001" | "text-davinci-001" | "text-davinci-002" | "text-davinci-003" | "ada" | "babbage" | "curie" | "davinci" | "code-davinci-002" | "code-davinci-001" | "davinci-codex" | "code-davinci-edit-001" | "code-cushman-002" | "code-cushman-001" | "cushman-codex" | "code-search-ada-code-001" | "code-search-ada-text-001" | "text-davinci-edit-001" | "text-similarity-ada-001" | "text-search-ada-doc-001" | "text-search-ada-query-001" | "text-similarity-babbage-001" | "text-search-babbage-doc-001" | "text-search-babbage-query-001" | "code-search-babbage-code-001" | "code-search-babbage-text-001" | "text-similarity-curie-001" | "text-search-curie-doc-001" | "text-search-curie-query-001" | "text-similarity-davinci-001" | "text-search-davinci-doc-001" | "text-search-davinci-query-001" | undefined) => Generator<number[], void, undefined>, vocabularySize: number;
|
|
5
|
+
export { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeChat, encodeChatGenerator, encodeGenerator, isWithinTokenLimit, vocabularySize, };
|
|
6
6
|
export default api;
|
|
@@ -17,14 +17,14 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
|
17
17
|
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
18
18
|
};
|
|
19
19
|
Object.defineProperty(exports, "__esModule", { value: true });
|
|
20
|
-
exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
20
|
+
exports.vocabularySize = exports.isWithinTokenLimit = exports.encodeGenerator = exports.encodeChatGenerator = exports.encodeChat = exports.encode = exports.decodeGenerator = exports.decodeAsyncGenerator = exports.decode = void 0;
|
|
21
21
|
/* eslint-disable import/extensions */
|
|
22
22
|
const cl100k_base_js_1 = __importDefault(require("../bpeRanks/cl100k_base.js"));
|
|
23
23
|
const GptEncoding_js_1 = require("../GptEncoding.js");
|
|
24
24
|
__exportStar(require("../specialTokens.js"), exports);
|
|
25
25
|
// prettier-ignore
|
|
26
26
|
const api = GptEncoding_js_1.GptEncoding.getEncodingApiForModel('gpt-3.5-turbo-0301', () => cl100k_base_js_1.default);
|
|
27
|
-
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, } = api;
|
|
27
|
+
const { decode, decodeAsyncGenerator, decodeGenerator, encode, encodeGenerator, isWithinTokenLimit, encodeChat, encodeChatGenerator, vocabularySize, } = api;
|
|
28
28
|
exports.decode = decode;
|
|
29
29
|
exports.decodeAsyncGenerator = decodeAsyncGenerator;
|
|
30
30
|
exports.decodeGenerator = decodeGenerator;
|
|
@@ -33,6 +33,7 @@ exports.encodeGenerator = encodeGenerator;
|
|
|
33
33
|
exports.isWithinTokenLimit = isWithinTokenLimit;
|
|
34
34
|
exports.encodeChat = encodeChat;
|
|
35
35
|
exports.encodeChatGenerator = encodeChatGenerator;
|
|
36
|
+
exports.vocabularySize = vocabularySize;
|
|
36
37
|
// eslint-disable-next-line import/no-default-export
|
|
37
38
|
exports.default = api;
|
|
38
39
|
//# sourceMappingURL=gpt-3.5-turbo-0301.js.map
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"gpt-3.5-turbo-0301.js","sourceRoot":"","sources":["../../src/model/gpt-3.5-turbo-0301.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AACnC,kBAAkB;AAClB,MAAM,GAAG,GAAG,4BAAW,CAAC,sBAAsB,CAAC,oBAAoB,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACpF,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,
|
|
1
|
+
{"version":3,"file":"gpt-3.5-turbo-0301.js","sourceRoot":"","sources":["../../src/model/gpt-3.5-turbo-0301.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA,sCAAsC;AACtC,gFAAiD;AACjD,sDAA+C;AAE/C,sDAAmC;AACnC,kBAAkB;AAClB,MAAM,GAAG,GAAG,4BAAW,CAAC,sBAAsB,CAAC,oBAAoB,EAAE,GAAG,EAAE,CAAC,wBAAQ,CAAC,CAAA;AACpF,MAAM,EACJ,MAAM,EACN,oBAAoB,EACpB,eAAe,EACf,MAAM,EACN,eAAe,EACf,kBAAkB,EAClB,UAAU,EACV,mBAAmB,EACnB,cAAc,GACf,GAAG,GAAG,CAAA;AAEL,wBAAM;AACN,oDAAoB;AACpB,0CAAe;AACf,wBAAM;AAGN,0CAAe;AACf,gDAAkB;AAHlB,gCAAU;AACV,kDAAmB;AAGnB,wCAAc;AAEhB,oDAAoD;AACpD,kBAAe,GAAG,CAAA"}
|