{"_id":"@cyberlangke/tokkit-pleias","name":"@cyberlangke/tokkit-pleias","dist-tags":{"latest":"1.11.0"},"versions":{"1.11.0":{"name":"@cyberlangke/tokkit-pleias","version":"1.11.0","description":"PleIAs tokenizer families for tokkit.","type":"module","main":"./dist/index.cjs","module":"./dist/index.js","types":"./dist/index.d.ts","exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js","require":"./dist/index.cjs"}},"scripts":{"build":"tsup","dev":"tsup --watch"},"dependencies":{"@cyberlangke/tokkit-core":"1.11.0"},"publishConfig":{"access":"public"},"repository":{"type":"git","url":"git+https://github.com/1cyberlangke1/tokkit.git"},"homepage":"https://github.com/1cyberlangke1/tokkit#readme","bugs":{"url":"https://github.com/1cyberlangke1/tokkit/issues"},"author":{"name":"cyberlangke"},"license":"Apache-2.0","gitHead":"cc928783a08a4fc42118eb6e696ec74fbfead48f","_id":"@cyberlangke/tokkit-pleias@1.11.0","_nodeVersion":"24.14.0","_npmVersion":"11.9.0","dist":{"integrity":"sha512-xEpZ+MGrjHGNT2FEboLbwfnIkSRjxFEbouFsXeUqYzYngX+RYd8a1ot3Q/5iujXiSpMYOIgUDy4OkYuqES2lYQ==","shasum":"d5f248d9d75c213a3d63b7c8ee852f2c9a496e8a","tarball":"https://registry.npmjs.org/@cyberlangke/tokkit-pleias/-/tokkit-pleias-1.11.0.tgz","fileCount":32,"unpackedSize":12347531,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIAW38R6GCovn4KhkV7HbFd/iA55QrQlSZ5hQUJRIrpLdAiBt7Q1592LbQ1ckUgTVDirQsgHmrcY54bNleE5NBU87fQ=="}]},"_npmUser":{"name":"cyberlangke","email":"3531702083@qq.com"},"directories":{},"maintainers":[{"name":"cyberlangke","email":"3531702083@qq.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/tokkit-pleias_1.11.0_1775102616872_0.4265051972042544"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-02T04:03:36.767Z","1.11.0":"2026-04-02T04:03:37.304Z","modified":"2026-04-02T04:03:37.522Z"},"maintainers":[{"name":"cyberlangke","email":"3531702083@qq.com"}],"description":"PleIAs tokenizer families for tokkit.","homepage":"https://github.com/1cyberlangke1/tokkit#readme","repository":{"type":"git","url":"git+https://github.com/1cyberlangke1/tokkit.git"},"author":{"name":"cyberlangke"},"bugs":{"url":"https://github.com/1cyberlangke1/tokkit/issues"},"license":"Apache-2.0","readme":"# @cyberlangke/tokkit-pleias\n\nPleIAs 官方文本模型的 tokkit 子包。\n\n当前纳入的官方主线模型：\n\n- `PleIAs/Pleias-350m-Preview`\n- `PleIAs/Pleias-1.2b-Preview`\n- `PleIAs/Pleias-3b-Preview`\n- `PleIAs/Pleias-Pico`\n- `PleIAs/Baguettotron`\n- `PleIAs/Monad`\n\n当前不纳入：\n\n- `PleIAs/Pleias-RAG-350M`\n- `PleIAs/Pleias-RAG-1B`\n- `PleIAs/OCRonos`\n\n说明：\n\n- 当前纳入的 `6` 个官方主线模型都公开 `tokenizer.json`，且都属于标准 `BPE + Split + ByteLevel` 路线。\n- `Pleias-RAG-*` 当前模型页明确带有 `base_model:finetune:*` 标记，不纳入。\n- `OCRonos` 是 OCR / 文档专项线，不纳入当前主线。\n\n## 使用方法\n\n```bash\nnpm install @cyberlangke/tokkit-pleias\n```\n\n```ts\nimport { getEncoding } from \"@cyberlangke/tokkit-pleias\"\n\nconst pleias = await getEncoding(\"PleIAs/Pleias-350m-Preview\")\nconst monad = await getEncoding(\"PleIAs/Monad\")\n\nconsole.log(pleias.encode(\"Hello, PleIAs\"))\nconsole.log(monad.encode(\"Hello, Monad\"))\n```\n","readmeFilename":"README.md","_rev":"1-8cfbcfaca9f7aa7ca8d672ece078bf22"}