Instructions to use apus-ailab/APUS-Reflex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apus-ailab/APUS-Reflex with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("apus-ailab/APUS-Reflex", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download effort-tradeoff-data.json from apus-ailab/APUS-Reflex: direct link, hf CLI and curl.
- Browser
- Download file 1.61 kB
-
https://huggingface.co/apus-ailab/APUS-Reflex/resolve/main/effort-tradeoff-data.json
- Command line
-
hf download hf://apus-ailab/APUS-Reflex/effort-tradeoff-data.json
-
curl -L -o effort-tradeoff-data.json https://huggingface.co/apus-ailab/APUS-Reflex/resolve/main/effort-tradeoff-data.json
1.61 kB
| { | |
| "selected_model": "4B-5949", | |
| "display": "4B accuracy comparison plus separately attributed 9B high HTTP snapshot; historical native timings retained below only as provenance", | |
| "http_reference": { | |
| "model": "9B-5949", | |
| "effort": "high", | |
| "p50_ms": 25.58, | |
| "p95_ms": 222.36, | |
| "p99_ms": 275.58, | |
| "hardware": "1x RTX PRO 6000 Blackwell 96GB", | |
| "source": "User-provided run screenshot and high-effort clarification" | |
| }, | |
| "source_path": "evidence/official-vs-final5949-80/report.json", | |
| "source_sha256": "b3542b7268a675a48c64ee0dad067bbb609c0e3c99bc6f7926e0241a56a27597", | |
| "low": { | |
| "n": 80, | |
| "correct": 61, | |
| "accuracy": 0.7625, | |
| "nll_epsilon_1e-12": 1.0545613467438772, | |
| "brier": 0.3943826629642137, | |
| "latency_p50_seconds": 0.05147563456557691, | |
| "latency_p95_seconds_nearest_rank": 0.19832013035193086 | |
| }, | |
| "high": { | |
| "n": 80, | |
| "correct": 66, | |
| "accuracy": 0.825, | |
| "nll_epsilon_1e-12": 0.6519612054580076, | |
| "brier": 0.27633044836807164, | |
| "latency_p50_seconds": 0.08542586304247379, | |
| "latency_p95_seconds_nearest_rank": 0.40630325907841325 | |
| }, | |
| "p50_ratio_high_over_low": 1.6595397757291617, | |
| "p95_ratio_high_over_low": 2.048724243763878, | |
| "p50_latency_reduction_percent": 39.74233009506361, | |
| "accuracy_drop_percentage_points": 6.25, | |
| "accuracy_relative_drop_percent": 7.575757575757576, | |
| "timing": "Historical single-request native forward; same checkpoint and frozen panel, not vLLM HTTP or merged latency retest", | |
| "routing": "Caller-selected effort; not automatic per-question routing", | |
| "n_records": 80, | |
| "n_parent_groups": 79 | |
| } |