{"_id":"@cyberlangke/tokkit-sarvamai","name":"@cyberlangke/tokkit-sarvamai","dist-tags":{"latest":"1.11.0"},"versions":{"1.11.0":{"name":"@cyberlangke/tokkit-sarvamai","version":"1.11.0","description":"sarvamai 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":"6d7b164cdcb511e7f5815e7278708c780b05d938","_id":"@cyberlangke/tokkit-sarvamai@1.11.0","_nodeVersion":"24.14.0","_npmVersion":"11.9.0","dist":{"integrity":"sha512-2MtELkz3SvoYgUiCjGrRDkavvkuDscaoYd1Fz404uOzBQtBPP6mZLuhVdaks6phbm98nXSVM/rKFizgBC+RvSw==","shasum":"d9c18cf7193d70c90a83e687c68752c0e7b8a343","tarball":"https://registry.npmjs.org/@cyberlangke/tokkit-sarvamai/-/tokkit-sarvamai-1.11.0.tgz","fileCount":12,"unpackedSize":12510449,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIB8IDqX1mW8qxooNsjy+c7Yz0Cwir0eQTEBK9c0dsWrPAiBDEfEugtdGkL/NUXD1lbHW7SC84E88+mngiVLTGSpMuw=="}]},"_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-sarvamai_1.11.0_1775230290743_0.015105231259849639"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-03T15:31:30.632Z","1.11.0":"2026-04-03T15:31:31.166Z","modified":"2026-04-03T15:31:31.429Z"},"maintainers":[{"name":"cyberlangke","email":"3531702083@qq.com"}],"description":"sarvamai 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-sarvamai\n\nsarvamai 官方文本 tokenizer 的 tokkit 子包。\n\n当前内置 family：\n\n- `sarvam-30b`\n  - 覆盖 `sarvamai/sarvam-30b`\n  - 也聚合当前确认完全复用同一 tokenizer 的 `sarvamai/sarvam-105b`\n- `sarvam-m`\n  - 覆盖 `sarvamai/sarvam-m`\n\n当前不纳入：\n\n- `sarvamai/sarvam-30b-fp8`\n- `sarvamai/sarvam-105b-fp8`\n- `sarvamai/sarvam-30b-gguf`\n- `sarvamai/sarvam-105b-gguf`\n- `sarvamai/sarvam-1`\n- `sarvamai/sarvam-1-v0.5`\n\n说明：\n\n- 当前纳入范围只包含 `sarvamai` 官方组织下公开可下载、许可证满足当前 MIT / Apache-2.0 边界、且落在纯文本 BPE 范围内的主线模型。\n- `sarvam-30b-fp8`、`sarvam-105b-fp8`、`sarvam-30b-gguf`、`sarvam-105b-gguf` 都属于发布格式衍生物，不作为独立支持目标。\n- `sarvam-1` 当前许可证信号为空，先不默认纳入。\n- `sarvam-1-v0.5` 当前是 `license: other`，不进入这一批。\n- `sarvam-30b` 与 `sarvam-105b` 的 `tokenizer.json` SHA256 一致，因此收口到同一个 `sarvam-30b` family。\n\n## 使用方法\n\n```bash\nnpm install @cyberlangke/tokkit-sarvamai\n```\n\n```ts\nimport { getTokenizer } from \"@cyberlangke/tokkit-sarvamai\"\n\nconst dense = await getTokenizer(\"sarvamai/sarvam-105b\")\nconst lightweight = await getTokenizer(\"sarvam-m\")\n\nconsole.log(dense !== lightweight)\n```\n","readmeFilename":"README.md","_rev":"1-cfce14e8acac38c0a58d3127934fb096"}