gpt-tokenizer 2.1.0 → 2.1.1
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/cjs/encoding/cl100k_base.d.ts +1 -1
- package/cjs/encoding/cl100k_base.js +4 -4
- package/cjs/encoding/cl100k_base.js.map +1 -1
- package/cjs/encoding/p50k_base.d.ts +1 -1
- package/cjs/encoding/p50k_base.js +4 -4
- package/cjs/encoding/p50k_base.js.map +1 -1
- package/cjs/encoding/p50k_edit.d.ts +1 -1
- package/cjs/encoding/p50k_edit.js +4 -4
- package/cjs/encoding/p50k_edit.js.map +1 -1
- package/cjs/encoding/r50k_base.d.ts +1 -1
- package/cjs/encoding/r50k_base.js +4 -4
- package/cjs/encoding/r50k_base.js.map +1 -1
- package/cjs/main.d.ts +1 -0
- package/cjs/main.js +7 -0
- package/cjs/main.js.map +1 -1
- package/cjs/model/ada.d.ts +1 -0
- package/cjs/model/ada.js +7 -0
- package/cjs/model/ada.js.map +1 -1
- package/cjs/model/babbage.d.ts +1 -0
- package/cjs/model/babbage.js +7 -0
- package/cjs/model/babbage.js.map +1 -1
- package/cjs/model/code-cushman-001.d.ts +1 -0
- package/cjs/model/code-cushman-001.js +7 -0
- package/cjs/model/code-cushman-001.js.map +1 -1
- package/cjs/model/code-cushman-002.d.ts +1 -0
- package/cjs/model/code-cushman-002.js +7 -0
- package/cjs/model/code-cushman-002.js.map +1 -1
- package/cjs/model/code-davinci-001.d.ts +1 -0
- package/cjs/model/code-davinci-001.js +7 -0
- package/cjs/model/code-davinci-001.js.map +1 -1
- package/cjs/model/code-davinci-002.d.ts +1 -0
- package/cjs/model/code-davinci-002.js +7 -0
- package/cjs/model/code-davinci-002.js.map +1 -1
- package/cjs/model/code-davinci-edit-001.d.ts +1 -0
- package/cjs/model/code-davinci-edit-001.js +7 -0
- package/cjs/model/code-davinci-edit-001.js.map +1 -1
- package/cjs/model/code-search-ada-code-001.d.ts +1 -0
- package/cjs/model/code-search-ada-code-001.js +7 -0
- package/cjs/model/code-search-ada-code-001.js.map +1 -1
- package/cjs/model/code-search-babbage-code-001.d.ts +1 -0
- package/cjs/model/code-search-babbage-code-001.js +7 -0
- package/cjs/model/code-search-babbage-code-001.js.map +1 -1
- package/cjs/model/curie.d.ts +1 -0
- package/cjs/model/curie.js +7 -0
- package/cjs/model/curie.js.map +1 -1
- package/cjs/model/cushman-codex.d.ts +1 -0
- package/cjs/model/cushman-codex.js +7 -0
- package/cjs/model/cushman-codex.js.map +1 -1
- package/cjs/model/davinci-codex.d.ts +1 -0
- package/cjs/model/davinci-codex.js +7 -0
- package/cjs/model/davinci-codex.js.map +1 -1
- package/cjs/model/davinci.d.ts +1 -0
- package/cjs/model/davinci.js +7 -0
- package/cjs/model/davinci.js.map +1 -1
- package/cjs/model/text-ada-001.d.ts +1 -0
- package/cjs/model/text-ada-001.js +7 -0
- package/cjs/model/text-ada-001.js.map +1 -1
- package/cjs/model/text-babbage-001.d.ts +1 -0
- package/cjs/model/text-babbage-001.js +7 -0
- package/cjs/model/text-babbage-001.js.map +1 -1
- package/cjs/model/text-curie-001.d.ts +1 -0
- package/cjs/model/text-curie-001.js +7 -0
- package/cjs/model/text-curie-001.js.map +1 -1
- package/cjs/model/text-davinci-001.d.ts +1 -0
- package/cjs/model/text-davinci-001.js +7 -0
- package/cjs/model/text-davinci-001.js.map +1 -1
- package/cjs/model/text-davinci-002.d.ts +1 -0
- package/cjs/model/text-davinci-002.js +7 -0
- package/cjs/model/text-davinci-002.js.map +1 -1
- package/cjs/model/text-davinci-003.d.ts +1 -0
- package/cjs/model/text-davinci-003.js +7 -0
- package/cjs/model/text-davinci-003.js.map +1 -1
- package/cjs/model/text-davinci-edit-001.d.ts +1 -0
- package/cjs/model/text-davinci-edit-001.js +7 -0
- package/cjs/model/text-davinci-edit-001.js.map +1 -1
- package/cjs/model/text-embedding-ada-002.d.ts +1 -0
- package/cjs/model/text-embedding-ada-002.js +7 -0
- package/cjs/model/text-embedding-ada-002.js.map +1 -1
- package/cjs/model/text-search-ada-doc-001.d.ts +1 -0
- package/cjs/model/text-search-ada-doc-001.js +7 -0
- package/cjs/model/text-search-ada-doc-001.js.map +1 -1
- package/cjs/model/text-search-babbage-doc-001.d.ts +1 -0
- package/cjs/model/text-search-babbage-doc-001.js +7 -0
- package/cjs/model/text-search-babbage-doc-001.js.map +1 -1
- package/cjs/model/text-search-curie-doc-001.d.ts +1 -0
- package/cjs/model/text-search-curie-doc-001.js +7 -0
- package/cjs/model/text-search-curie-doc-001.js.map +1 -1
- package/cjs/model/text-search-davinci-doc-001.d.ts +1 -0
- package/cjs/model/text-search-davinci-doc-001.js +7 -0
- package/cjs/model/text-search-davinci-doc-001.js.map +1 -1
- package/cjs/model/text-similarity-ada-001.d.ts +1 -0
- package/cjs/model/text-similarity-ada-001.js +7 -0
- package/cjs/model/text-similarity-ada-001.js.map +1 -1
- package/cjs/model/text-similarity-babbage-001.d.ts +1 -0
- package/cjs/model/text-similarity-babbage-001.js +7 -0
- package/cjs/model/text-similarity-babbage-001.js.map +1 -1
- package/cjs/model/text-similarity-curie-001.d.ts +1 -0
- package/cjs/model/text-similarity-curie-001.js +7 -0
- package/cjs/model/text-similarity-curie-001.js.map +1 -1
- package/cjs/model/text-similarity-davinci-001.d.ts +1 -0
- package/cjs/model/text-similarity-davinci-001.js +7 -0
- package/cjs/model/text-similarity-davinci-001.js.map +1 -1
- package/dist/cl100k_base.js +1 -1
- package/dist/cl100k_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/codegen/generateByModel.js +1 -1
- package/esm/codegen/generateByModel.js.map +1 -1
- package/esm/encoding/cl100k_base.d.ts +1 -1
- package/esm/encoding/cl100k_base.js +1 -1
- package/esm/encoding/cl100k_base.js.map +1 -1
- package/esm/encoding/p50k_base.d.ts +1 -1
- package/esm/encoding/p50k_base.js +1 -1
- package/esm/encoding/p50k_base.js.map +1 -1
- package/esm/encoding/p50k_edit.d.ts +1 -1
- package/esm/encoding/p50k_edit.js +1 -1
- package/esm/encoding/p50k_edit.js.map +1 -1
- package/esm/encoding/r50k_base.d.ts +1 -1
- package/esm/encoding/r50k_base.js +1 -1
- package/esm/encoding/r50k_base.js.map +1 -1
- package/esm/main.d.ts +1 -0
- package/esm/main.js +2 -0
- package/esm/main.js.map +1 -1
- package/esm/model/ada.d.ts +1 -0
- package/esm/model/ada.js +2 -0
- package/esm/model/ada.js.map +1 -1
- package/esm/model/babbage.d.ts +1 -0
- package/esm/model/babbage.js +2 -0
- package/esm/model/babbage.js.map +1 -1
- package/esm/model/code-cushman-001.d.ts +1 -0
- package/esm/model/code-cushman-001.js +2 -0
- package/esm/model/code-cushman-001.js.map +1 -1
- package/esm/model/code-cushman-002.d.ts +1 -0
- package/esm/model/code-cushman-002.js +2 -0
- package/esm/model/code-cushman-002.js.map +1 -1
- package/esm/model/code-davinci-001.d.ts +1 -0
- package/esm/model/code-davinci-001.js +2 -0
- package/esm/model/code-davinci-001.js.map +1 -1
- package/esm/model/code-davinci-002.d.ts +1 -0
- package/esm/model/code-davinci-002.js +2 -0
- package/esm/model/code-davinci-002.js.map +1 -1
- package/esm/model/code-davinci-edit-001.d.ts +1 -0
- package/esm/model/code-davinci-edit-001.js +2 -0
- package/esm/model/code-davinci-edit-001.js.map +1 -1
- package/esm/model/code-search-ada-code-001.d.ts +1 -0
- package/esm/model/code-search-ada-code-001.js +2 -0
- package/esm/model/code-search-ada-code-001.js.map +1 -1
- package/esm/model/code-search-babbage-code-001.d.ts +1 -0
- package/esm/model/code-search-babbage-code-001.js +2 -0
- package/esm/model/code-search-babbage-code-001.js.map +1 -1
- package/esm/model/curie.d.ts +1 -0
- package/esm/model/curie.js +2 -0
- package/esm/model/curie.js.map +1 -1
- package/esm/model/cushman-codex.d.ts +1 -0
- package/esm/model/cushman-codex.js +2 -0
- package/esm/model/cushman-codex.js.map +1 -1
- package/esm/model/davinci-codex.d.ts +1 -0
- package/esm/model/davinci-codex.js +2 -0
- package/esm/model/davinci-codex.js.map +1 -1
- package/esm/model/davinci.d.ts +1 -0
- package/esm/model/davinci.js +2 -0
- package/esm/model/davinci.js.map +1 -1
- package/esm/model/text-ada-001.d.ts +1 -0
- package/esm/model/text-ada-001.js +2 -0
- package/esm/model/text-ada-001.js.map +1 -1
- package/esm/model/text-babbage-001.d.ts +1 -0
- package/esm/model/text-babbage-001.js +2 -0
- package/esm/model/text-babbage-001.js.map +1 -1
- package/esm/model/text-curie-001.d.ts +1 -0
- package/esm/model/text-curie-001.js +2 -0
- package/esm/model/text-curie-001.js.map +1 -1
- package/esm/model/text-davinci-001.d.ts +1 -0
- package/esm/model/text-davinci-001.js +2 -0
- package/esm/model/text-davinci-001.js.map +1 -1
- package/esm/model/text-davinci-002.d.ts +1 -0
- package/esm/model/text-davinci-002.js +2 -0
- package/esm/model/text-davinci-002.js.map +1 -1
- package/esm/model/text-davinci-003.d.ts +1 -0
- package/esm/model/text-davinci-003.js +2 -0
- package/esm/model/text-davinci-003.js.map +1 -1
- package/esm/model/text-davinci-edit-001.d.ts +1 -0
- package/esm/model/text-davinci-edit-001.js +2 -0
- package/esm/model/text-davinci-edit-001.js.map +1 -1
- package/esm/model/text-embedding-ada-002.d.ts +1 -0
- package/esm/model/text-embedding-ada-002.js +2 -0
- package/esm/model/text-embedding-ada-002.js.map +1 -1
- package/esm/model/text-search-ada-doc-001.d.ts +1 -0
- package/esm/model/text-search-ada-doc-001.js +2 -0
- package/esm/model/text-search-ada-doc-001.js.map +1 -1
- package/esm/model/text-search-babbage-doc-001.d.ts +1 -0
- package/esm/model/text-search-babbage-doc-001.js +2 -0
- package/esm/model/text-search-babbage-doc-001.js.map +1 -1
- package/esm/model/text-search-curie-doc-001.d.ts +1 -0
- package/esm/model/text-search-curie-doc-001.js +2 -0
- package/esm/model/text-search-curie-doc-001.js.map +1 -1
- package/esm/model/text-search-davinci-doc-001.d.ts +1 -0
- package/esm/model/text-search-davinci-doc-001.js +2 -0
- package/esm/model/text-search-davinci-doc-001.js.map +1 -1
- package/esm/model/text-similarity-ada-001.d.ts +1 -0
- package/esm/model/text-similarity-ada-001.js +2 -0
- package/esm/model/text-similarity-ada-001.js.map +1 -1
- package/esm/model/text-similarity-babbage-001.d.ts +1 -0
- package/esm/model/text-similarity-babbage-001.js +2 -0
- package/esm/model/text-similarity-babbage-001.js.map +1 -1
- package/esm/model/text-similarity-curie-001.d.ts +1 -0
- package/esm/model/text-similarity-curie-001.js +2 -0
- package/esm/model/text-similarity-curie-001.js.map +1 -1
- package/esm/model/text-similarity-davinci-001.d.ts +1 -0
- package/esm/model/text-similarity-davinci-001.js +2 -0
- package/esm/model/text-similarity-davinci-001.js.map +1 -1
- package/package.json +5 -5
- package/src/codegen/generateByModel.ts +1 -1
- package/src/encoding/cl100k_base.ts +1 -1
- package/src/encoding/p50k_base.ts +1 -1
- package/src/encoding/p50k_edit.ts +1 -1
- package/src/encoding/r50k_base.ts +1 -1
- package/src/main.ts +2 -0
- package/src/model/ada.ts +2 -0
- package/src/model/babbage.ts +2 -0
- package/src/model/code-cushman-001.ts +2 -0
- package/src/model/code-cushman-002.ts +2 -0
- package/src/model/code-davinci-001.ts +2 -0
- package/src/model/code-davinci-002.ts +2 -0
- package/src/model/code-davinci-edit-001.ts +2 -0
- package/src/model/code-search-ada-code-001.ts +2 -0
- package/src/model/code-search-babbage-code-001.ts +2 -0
- package/src/model/curie.ts +2 -0
- package/src/model/cushman-codex.ts +2 -0
- package/src/model/davinci-codex.ts +2 -0
- package/src/model/davinci.ts +2 -0
- package/src/model/text-ada-001.ts +2 -0
- package/src/model/text-babbage-001.ts +2 -0
- package/src/model/text-curie-001.ts +2 -0
- package/src/model/text-davinci-001.ts +2 -0
- package/src/model/text-davinci-002.ts +2 -0
- package/src/model/text-davinci-003.ts +2 -0
- package/src/model/text-davinci-edit-001.ts +2 -0
- package/src/model/text-embedding-ada-002.ts +2 -0
- package/src/model/text-search-ada-doc-001.ts +2 -0
- package/src/model/text-search-babbage-doc-001.ts +2 -0
- package/src/model/text-search-curie-doc-001.ts +2 -0
- package/src/model/text-search-davinci-doc-001.ts +2 -0
- package/src/model/text-similarity-ada-001.ts +2 -0
- package/src/model/text-similarity-babbage-001.ts +2 -0
- package/src/model/text-similarity-curie-001.ts +2 -0
- package/src/model/text-similarity-davinci-001.ts +2 -0
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"text-similarity-babbage-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-babbage-001.ts"],"names":[],"mappings":"AAAA,cAAc,0BAA0B,CAAA"}
|
|
1
|
+
{"version":3,"file":"text-similarity-babbage-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-babbage-001.ts"],"names":[],"mappings":"AAAA,2EAA2E;AAC3E,OAAO,EAAE,OAAO,EAAE,MAAM,0BAA0B,CAAA;AAClD,cAAc,0BAA0B,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"text-similarity-curie-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-curie-001.ts"],"names":[],"mappings":"AAAA,cAAc,0BAA0B,CAAA"}
|
|
1
|
+
{"version":3,"file":"text-similarity-curie-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-curie-001.ts"],"names":[],"mappings":"AAAA,2EAA2E;AAC3E,OAAO,EAAE,OAAO,EAAE,MAAM,0BAA0B,CAAA;AAClD,cAAc,0BAA0B,CAAA"}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"text-similarity-davinci-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-davinci-001.ts"],"names":[],"mappings":"AAAA,cAAc,0BAA0B,CAAA"}
|
|
1
|
+
{"version":3,"file":"text-similarity-davinci-001.js","sourceRoot":"","sources":["../../src/model/text-similarity-davinci-001.ts"],"names":[],"mappings":"AAAA,2EAA2E;AAC3E,OAAO,EAAE,OAAO,EAAE,MAAM,0BAA0B,CAAA;AAClD,cAAc,0BAA0B,CAAA"}
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "gpt-tokenizer",
|
|
3
|
-
"version": "2.1.
|
|
3
|
+
"version": "2.1.1",
|
|
4
4
|
"description": "A pure JavaScript implementation of a BPE tokenizer (Encoder/Decoder) for GPT-2 / GPT-3 / GPT-4 and other OpenAI models",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"BPE",
|
|
@@ -78,10 +78,10 @@
|
|
|
78
78
|
"build:cjs": "yarn rrun tsc --outDir cjs --module commonjs --target es2022 --project tsconfig-cjs.json",
|
|
79
79
|
"build:esm": "yarn rrun tsc --outDir esm --module esnext --target es2022 && echo '{\"name\": \"gpt-tokenizer\", \"type\": \"module\"}' > ./esm/package.json",
|
|
80
80
|
"build:umd": "yarn build:umd:cl100k_base && yarn build:umd:p50k_base && yarn build:umd:p50k_edit && yarn build:umd:r50k_base",
|
|
81
|
-
"build:umd:cl100k_base": "beemo webpack --entry='./src/main.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_cl100k_base' --env '
|
|
82
|
-
"build:umd:p50k_base": "beemo webpack --entry='./src/encoding/p50k_base.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_p50k_base' --env '
|
|
83
|
-
"build:umd:p50k_edit": "beemo webpack --entry='./src/encoding/p50k_edit.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_p50k_edit' --env '
|
|
84
|
-
"build:umd:r50k_base": "beemo webpack --entry='./src/encoding/r50k_base.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_r50k_base' --env '
|
|
81
|
+
"build:umd:cl100k_base": "beemo webpack --entry='./src/main.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_cl100k_base' --env 'filename=cl100k_base.js'",
|
|
82
|
+
"build:umd:p50k_base": "beemo webpack --entry='./src/encoding/p50k_base.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_p50k_base' --env 'filename=p50k_base.js'",
|
|
83
|
+
"build:umd:p50k_edit": "beemo webpack --entry='./src/encoding/p50k_edit.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_p50k_edit' --env 'filename=p50k_edit.js'",
|
|
84
|
+
"build:umd:r50k_base": "beemo webpack --entry='./src/encoding/r50k_base.ts' --env 'outDir=dist' --env 'moduleTarget=umd' --env 'engineTarget=web' --env 'codeTarget=es2022' --env 'name=GPTTokenizer_r50k_base' --env 'filename=r50k_base.js'",
|
|
85
85
|
"clean": "git clean -dfX --exclude=node_modules src && beemo typescript:sync-project-refs",
|
|
86
86
|
"format": "yarn rrun prettier --write \"./{src,tests,.config}/**/!(*.d).{.js,jsx,ts,tsx,json,md}\"",
|
|
87
87
|
"postinstallDev": "yarn prepare",
|
|
@@ -23,7 +23,7 @@ await Promise.all(
|
|
|
23
23
|
`getEncodingApi('cl100k_base'`,
|
|
24
24
|
`getEncodingApiForModel('${modelName}'`,
|
|
25
25
|
)
|
|
26
|
-
:
|
|
26
|
+
: `// eslint-disable-next-line no-restricted-exports, import/no-default-export\nexport { default } from '../encoding/${encoding}.js'\nexport * from '../encoding/${encoding}.js'\n`
|
|
27
27
|
await fs.writeFile(
|
|
28
28
|
path.join(__dirname, `../model/${modelName}.ts`),
|
|
29
29
|
content,
|
|
@@ -5,7 +5,7 @@ import { GptEncoding } from '../GptEncoding.js'
|
|
|
5
5
|
|
|
6
6
|
export * from '../specialTokens.js'
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
const api = GptEncoding.getEncodingApi('cl100k_base', () =>
|
|
9
9
|
convertTokenBytePairEncodingFromTuples(encoder),
|
|
10
10
|
)
|
|
11
11
|
const {
|
|
@@ -5,7 +5,7 @@ import { GptEncoding } from '../GptEncoding.js'
|
|
|
5
5
|
|
|
6
6
|
export * from '../specialTokens.js'
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
const api = GptEncoding.getEncodingApi('p50k_base', () =>
|
|
9
9
|
convertTokenBytePairEncodingFromTuples(encoder),
|
|
10
10
|
)
|
|
11
11
|
const {
|
|
@@ -5,7 +5,7 @@ import { GptEncoding } from '../GptEncoding.js'
|
|
|
5
5
|
|
|
6
6
|
export * from '../specialTokens.js'
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
const api = GptEncoding.getEncodingApi('p50k_edit', () =>
|
|
9
9
|
convertTokenBytePairEncodingFromTuples(encoder),
|
|
10
10
|
)
|
|
11
11
|
const {
|
|
@@ -5,7 +5,7 @@ import { GptEncoding } from '../GptEncoding.js'
|
|
|
5
5
|
|
|
6
6
|
export * from '../specialTokens.js'
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
const api = GptEncoding.getEncodingApi('r50k_base', () =>
|
|
9
9
|
convertTokenBytePairEncodingFromTuples(encoder),
|
|
10
10
|
)
|
|
11
11
|
const {
|
package/src/main.ts
CHANGED
package/src/model/ada.ts
CHANGED
package/src/model/babbage.ts
CHANGED
package/src/model/curie.ts
CHANGED
package/src/model/davinci.ts
CHANGED