Views
No views yet
medium PJ OCR document parsing pipeline. The model set preserves MinerU-compatible document structure and is intended to run locally in the browser through jax-js and WebGPU.contract.json records the upstream Hugging Face repository, pinned source revision, source file checksums, conversion contract, and upstream license provenance.| Pipeline role | Artifact | Weight dtype | Weight bytes |
|---|---|---|---|
| Layout detection | pp-doclayout-v3-fp16-jaxjs | FP16 | 65,459,939 |
| Layout verification/rollback | pp-doclayout-v3-jaxjs | FP32 | 130,847,572 |
| Layout rollback | pp-doclayout-l-fp16-jaxjs | FP16 | 64,568,988 |
| Formula recognition | pp-formulanet-plus-s-fp16-jaxjs | FP16 | 128,454,765 |
| Table classification | mineru-table-classifier-jaxjs | FP32 | 6,753,977 |
| Table recognition | slanet-plus-table-jaxjs | Mixed | 6,593,062 |
| Wired table recovery | mineru-unet-structure-table-fp16-jaxjs | FP16 storage | 4,168,278 |
| OCR detection | ppocr-v6-medium-det-jaxjs | FP32 | 61,974,931 |
| OCR recognition | ppocr-v6-medium-rec-streaming-jaxjs | FP32 shards | 76,508,326 |
model-sets/medium.json. Canonical medium uses FP16 PP-DocLayoutV3, streaming PP-OCRv6 recognition, and the all-JAXJS MinerU table trio. The non-default model-sets/medium-v3-candidate.json preserves FP32 PP-DocLayoutV3 for release verification and explicit rollback.1model-sets/
2 medium.json
3models-jaxjs/
4 manifest.json
5 pp-doclayout-v3-fp16-jaxjs/
6 pp-doclayout-v3-jaxjs/
7 mineru-table-classifier-jaxjs/
8 slanet-plus-table-jaxjs/
9 mineru-unet-structure-table-fp16-jaxjs/
10 ppocr-v6-medium-rec-streaming-jaxjs/
11 pp-doclayout-l-fp16-jaxjs/
12 pp-formulanet-plus-s-fp16-jaxjs/
13 ppocr-v6-medium-det-jaxjs/
14 ppocr-v6-medium-rec-jaxjs/
15SHA256SUMScontract.json: loader and provenance contract, including the expected Safetensors checksum.metadata.json: converted Paddle graph plan and preprocessing/postprocessing metadata.weights.safetensors: active weights selected by the contract.sidecars/: inference configuration and dictionaries required by the model-specific loader.constants/: non-weight tensor shards when required. PP-DocLayout-L includes one boolean constant shard.1const repo = "hf-dev-01/pj-ocr-jaxjs-medium";
2const revision = "PINNED_COMMIT_SHA";
3const artifactBase = `https://huggingface.co/${repo}/resolve/${revision}/`;
4
5async function fetchArtifact(path: string): Promise<ArrayBuffer> {
6 const response = await fetch(new URL(path, artifactBase));
7 if (!response.ok) {
8 throw new Error(`Artifact fetch failed (${response.status}): ${path}`);
9 }
10 return response.arrayBuffer();
11}
12
13const manifest = await fetchArtifact("models-jaxjs/manifest.json");main in production so contracts, metadata, sidecars, and weights remain an atomic set. Cache immutable commit-pinned URLs in Cache Storage, OPFS, or another durable browser store.SHA256SUMS covers every packaged file other than itself. The weight checksum in each contract.json is also validated by the PJ OCR JAXJS artifact workflow.contract.json records its exact upstream repository, revision, and license. The repository includes both LICENSE and the applicable upstream notices under LICENSES/.pp-doclayout-v3-fp16-jaxjs is the canonical browser layout artifact. pp-doclayout-v3-jaxjs remains available for release verification and explicit rollback. See the V3 artifact report.medium selects mineru-table-classifier-jaxjs, slanet-plus-table-jaxjs, and mineru-unet-structure-table-fp16-jaxjs. The composed lane checksum-verifies their release descriptor, the streaming OCR descriptor, and the published V3 descriptor before writing the repository checksum inventory. The layout, streaming OCR, and table descriptors all pin immutable artifact revision 3ebf4493fe544793ad72ece74cf4777b281460d6.