Instructions to use apus-ailab/APUS-OpenJev-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apus-ailab/APUS-OpenJev-v1 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("apus-ailab/APUS-OpenJev-v1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download chart-data.json from apus-ailab/APUS-OpenJev-v1: direct link, hf CLI and curl.
- Browser
- Download file 4.5 kB
-
https://huggingface.co/apus-ailab/APUS-OpenJev-v1/resolve/main/chart-data.json
- Command line
-
hf download hf://apus-ailab/APUS-OpenJev-v1/chart-data.json
-
curl -L -o chart-data.json https://huggingface.co/apus-ailab/APUS-OpenJev-v1/resolve/main/chart-data.json
4.5 kB
| { | |
| "title": "APUS-OpenJev-v1", | |
| "created_date": "2026-09-21", | |
| "panel": { | |
| "records": 80, | |
| "parent_groups": 79, | |
| "task_counts": { | |
| "Browser": 16, | |
| "HelpSteer3": 16, | |
| "BoolQ": 16, | |
| "MNLI": 16, | |
| "Score": 16 | |
| }, | |
| "score_labels": "16 No, 0 Yes", | |
| "split": "validation/development regression; not sealed final", | |
| "laya_export_sha256": "26aa47e8f56c18a403eb4c8379d5cccb9cea5af97c191ab26ec36b8fb17ae923" | |
| }, | |
| "accuracy": [ | |
| { | |
| "model": "APUS-OpenJev 9B", | |
| "correct": 68, | |
| "total": 80, | |
| "percentage": 85.0, | |
| "source": "merged9b", | |
| "effort": "high", | |
| "variant_directory": "9B-3000" | |
| }, | |
| { | |
| "model": "APUS-OpenJev 4B", | |
| "correct": 66, | |
| "total": 80, | |
| "percentage": 82.5, | |
| "source": "merged4b", | |
| "effort": "high", | |
| "variant_directory": "4B-5949" | |
| }, | |
| { | |
| "model": "Jev official API", | |
| "correct": 66, | |
| "total": 80, | |
| "percentage": 82.5, | |
| "source": "native9b_latency" | |
| }, | |
| { | |
| "model": "Laya typed / full input", | |
| "correct": 55, | |
| "total": 80, | |
| "percentage": 68.75, | |
| "source": "laya_repeats", | |
| "config": "typed-fullinput", | |
| "repetitions": 3, | |
| "identical_accuracy": true, | |
| "truncations": 0 | |
| } | |
| ], | |
| "latency": { | |
| "native_forward_historical": [ | |
| { | |
| "model": "APUS-OpenJev 9B", | |
| "p50_ms": 77.76357303373516, | |
| "p95_ms": 505.1563191227615, | |
| "source": "native9b_latency" | |
| }, | |
| { | |
| "model": "APUS-OpenJev 4B", | |
| "p50_ms": 85.43, | |
| "p95_ms": 406.3, | |
| "source": "native4b_latency" | |
| } | |
| ], | |
| "laya_local_system_one": { | |
| "model": "Laya typed / full input", | |
| "p50_ms": 8.684632601216435, | |
| "p95_ms": 37.65514073893428, | |
| "p50_range_ms": [ | |
| 8.429150097072124, | |
| 8.730278117582202 | |
| ], | |
| "p95_range_ms": [ | |
| 37.441988941282034, | |
| 37.88864379748702 | |
| ], | |
| "aggregation": "median of three per-run P50 and P95 values; not pooled or fastest-run selection", | |
| "scope": "native system_one includes tokenization, transfer, forward and structured response; excludes HTTP and loading", | |
| "source": "laya_repeats" | |
| }, | |
| "official_http": { | |
| "model": "Jev official API", | |
| "p50_ms": 436.9597500190139, | |
| "p95_ms": 4874.612333020195, | |
| "scope": "remote full HTTP response including network/queue/service; not client-observable TTFT", | |
| "source": "native9b_latency" | |
| }, | |
| "cross_scope_speedup_claim": false, | |
| "merged_package_latency_retest": false | |
| }, | |
| "sources": { | |
| "laya_repeats": { | |
| "project_relative_path": "docs/feat-jev-combined/evidence/laya-repeated-20260921/summary.json", | |
| "sha256": "16a2d3a265909e40f65cdb9331417a6d46a1f2140759f94d2b183728d64825e6" | |
| }, | |
| "native9b_latency": { | |
| "project_relative_path": "docs/feat-jev-combined/evidence/9b-checkpoints80/3000/report.json", | |
| "sha256": "f3b93d04ab8e99d3cf135d410b559e1c96e980fba43c59b71428fe8c815b9303" | |
| }, | |
| "native4b_latency": { | |
| "project_relative_path": "docs/feat-jev-combined/official-typesafe-vs-final5949-80-20260920.md", | |
| "sha256": "5a7568a998d4be13555374399aa91e9b458d782336b14ab33603a2ebcabe99fc" | |
| }, | |
| "merged4b": { | |
| "project_relative_path": "docs/feat-jev-combined/openjet-release-20260921/merged-release/evidence/4B/comparison.json", | |
| "sha256": "97cc94ddebb4f321d3d4ed29c89a0d8b1b3d6570e48bff427c635ba82f67862e" | |
| }, | |
| "merged9b": { | |
| "project_relative_path": "docs/feat-jev-combined/openjet-release-20260921/merged-release/evidence/9B/comparison.json", | |
| "sha256": "d2ea8a7af10f09fdfde166384ffb18fb5a19ebf1a1281c58cb72806a45878c41" | |
| }, | |
| "panel_description": { | |
| "project_relative_path": "docs/feat-jev-combined/openjet-release-20260921/eval-dataset/SPLIT_AND_EVALUATION.md", | |
| "sha256": "b14b8af51f0527443b369f6995d46b786207dbf663ef2ce5afc9cc0a02d31b8b" | |
| } | |
| }, | |
| "limitations": [ | |
| "80 development questions are reused and have influenced development/version selection.", | |
| "Two more correct answers than Jev does not establish significant superiority or noninferiority.", | |
| "Score is all No; Browser is static candidate selection, not website completion.", | |
| "Laya full-input formatting was changed without retraining; three repeats do not increase independent sample size.", | |
| "Historical native forward, local system_one and remote HTTP are different timing boundaries." | |
| ] | |
| } | |