Instructions to use petra345/EfficiencyLatency-ModelRepo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use petra345/EfficiencyLatency-ModelRepo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="petra345/EfficiencyLatency-ModelRepo")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("petra345/EfficiencyLatency-ModelRepo") model = AutoModel.from_pretrained("petra345/EfficiencyLatency-ModelRepo") - Notebooks
- Google Colab
- Kaggle
| checkpoint,weighted_overall,latency_ms,efficiency_score,eligible,decision_note | |
| step_100,0.584,610,0.957,false,rejected: below quality_floor | |
| step_200,0.619,650,0.952,false,rejected: below quality_floor | |
| step_300,0.653,690,0.946,false,rejected: below quality_floor | |
| step_400,0.685,760,0.901,false,rejected: below quality_floor | |
| step_500,0.713,840,0.849,false,rejected: below quality_floor | |
| step_600,0.731,910,0.803,true,eligible but lower efficiency_score | |
| step_700,0.739,860,0.859,true,selected highest efficiency_score among quality-floor checkpoints | |
| step_800,0.741,990,0.748,true,eligible but lower efficiency_score | |
| step_900,0.746,1100,0.678,true,eligible but lower efficiency_score | |
| step_1000,0.752,1230,0.611,true,eligible but lower efficiency_score | |