scorebook 0.0.13__py3-none-any.whl → 0.0.15__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- scorebook/__init__.py +12 -5
- scorebook/cli/auth.py +1 -1
- scorebook/dashboard/__init__.py +1 -0
- scorebook/dashboard/create_project.py +91 -0
- scorebook/{trismik → dashboard}/credentials.py +57 -12
- scorebook/{trismik → dashboard}/upload_results.py +1 -1
- scorebook/eval_datasets/__init__.py +0 -4
- scorebook/eval_datasets/eval_dataset.py +4 -2
- scorebook/evaluate/__init__.py +1 -15
- scorebook/evaluate/_async/evaluate_async.py +36 -19
- scorebook/evaluate/_sync/evaluate.py +36 -19
- scorebook/evaluate/evaluate_helpers.py +4 -3
- scorebook/inference/__init__.py +1 -11
- scorebook/inference/clients/__init__.py +1 -8
- scorebook/inference/inference_pipeline.py +1 -1
- scorebook/metrics/README.md +121 -0
- scorebook/metrics/__init__.py +7 -16
- scorebook/metrics/accuracy.py +2 -6
- scorebook/metrics/bertscore.py +50 -0
- scorebook/metrics/bleu.py +82 -0
- scorebook/metrics/core/__init__.py +1 -0
- scorebook/metrics/{metric_base.py → core/metric_base.py} +1 -2
- scorebook/metrics/core/metric_registry.py +195 -0
- scorebook/metrics/exactmatch.py +95 -0
- scorebook/metrics/f1.py +96 -0
- scorebook/metrics/precision.py +84 -9
- scorebook/metrics/recall.py +94 -0
- scorebook/metrics/rouge.py +85 -0
- scorebook/score/__init__.py +0 -5
- scorebook/score/_async/score_async.py +3 -2
- scorebook/score/_sync/score.py +3 -2
- scorebook/score/score_helpers.py +29 -12
- scorebook/types.py +3 -3
- scorebook/utils/__init__.py +0 -22
- scorebook/utils/common_helpers.py +1 -1
- scorebook/utils/mock_llm/__init__.py +41 -0
- scorebook/utils/mock_llm/data/mock_llm_data.json +21970 -0
- scorebook/utils/progress_bars.py +58 -786
- scorebook-0.0.15.dist-info/METADATA +300 -0
- scorebook-0.0.15.dist-info/RECORD +110 -0
- {scorebook-0.0.13.dist-info → scorebook-0.0.15.dist-info}/WHEEL +1 -1
- tutorials/README.md +147 -0
- tutorials/__init__.py +5 -0
- tutorials/examples/1-score/1-scoring_model_accuracy.py +47 -0
- tutorials/examples/1-score/2-scoring_model_bleu.py +46 -0
- tutorials/examples/1-score/3-scoring_model_f1.py +64 -0
- tutorials/examples/1-score/4-scoring_model_rouge.py +64 -0
- tutorials/examples/1-score/5-scoring_model_exact_match.py +84 -0
- tutorials/examples/1-score/6-scoring_with_bertscore.py +57 -0
- tutorials/examples/1-score/__init__.py +0 -0
- tutorials/examples/2-evaluate/1-evaluating_local_models.py +106 -0
- tutorials/examples/2-evaluate/2-evaluating_local_models_with_batching.py +108 -0
- tutorials/examples/2-evaluate/3-evaluating_cloud_models.py +109 -0
- tutorials/examples/2-evaluate/4-evaluating_cloud_models_with_batching.py +170 -0
- tutorials/examples/2-evaluate/5-hyperparameter_sweeps.py +122 -0
- tutorials/examples/2-evaluate/6-inference_pipelines.py +141 -0
- tutorials/examples/3-evaluation_datasets/1-evaluation_datasets_from_files.py +110 -0
- tutorials/examples/3-evaluation_datasets/2-evaluation_datasets_from_huggingface.py +101 -0
- tutorials/examples/3-evaluation_datasets/3-evaluation_datasets_from_huggingface_with_yaml_configs.py +110 -0
- tutorials/examples/3-evaluation_datasets/example_datasets/basic_questions.csv +11 -0
- tutorials/examples/3-evaluation_datasets/example_datasets/basic_questions.json +42 -0
- tutorials/examples/3-evaluation_datasets/example_yaml_configs/Cais-MMLU.yaml +19 -0
- tutorials/examples/3-evaluation_datasets/example_yaml_configs/TIGER-Lab-MMLU-Pro.yaml +18 -0
- tutorials/examples/4-adaptive_evaluations/1-adaptive_evaluation.py +114 -0
- tutorials/examples/4-adaptive_evaluations/2-adaptive_dataset_splits.py +106 -0
- tutorials/examples/5-upload_results/1-uploading_score_results.py +92 -0
- tutorials/examples/5-upload_results/2-uploading_evaluate_results.py +117 -0
- tutorials/examples/5-upload_results/3-uploading_your_results.py +153 -0
- tutorials/examples/6-providers/aws/__init__.py +1 -0
- tutorials/examples/6-providers/aws/batch_example.py +219 -0
- tutorials/examples/6-providers/portkey/__init__.py +1 -0
- tutorials/examples/6-providers/portkey/batch_example.py +120 -0
- tutorials/examples/6-providers/portkey/messages_example.py +121 -0
- tutorials/examples/6-providers/vertex/__init__.py +1 -0
- tutorials/examples/6-providers/vertex/batch_example.py +166 -0
- tutorials/examples/6-providers/vertex/messages_example.py +142 -0
- tutorials/examples/__init__.py +0 -0
- tutorials/notebooks/1-scoring.ipynb +162 -0
- tutorials/notebooks/2-evaluating.ipynb +316 -0
- tutorials/notebooks/3.1-adaptive_evaluation_phi.ipynb +354 -0
- tutorials/notebooks/3.2-adaptive_evaluation_gpt.ipynb +243 -0
- tutorials/notebooks/4-uploading_results.ipynb +175 -0
- tutorials/quickstarts/adaptive_evaluations/adaptive_evaluation_openai_demo.ipynb +229 -0
- tutorials/quickstarts/adaptive_evaluations/adaptive_evaluation_qwen_demo.ipynb +256 -0
- tutorials/quickstarts/classical_evaluations/classical_evaluation_demo.ipynb +277 -0
- tutorials/quickstarts/getting_started.ipynb +197 -0
- tutorials/utils/__init__.py +35 -0
- tutorials/utils/args_parser.py +132 -0
- tutorials/utils/output.py +23 -0
- tutorials/utils/setup.py +98 -0
- scorebook/metrics/metric_registry.py +0 -105
- scorebook/trismik/__init__.py +0 -10
- scorebook-0.0.13.dist-info/METADATA +0 -389
- scorebook-0.0.13.dist-info/RECORD +0 -50
- {scorebook-0.0.13.dist-info → scorebook-0.0.15.dist-info}/entry_points.txt +0 -0
- {scorebook-0.0.13.dist-info → scorebook-0.0.15.dist-info}/licenses/LICENSE +0 -0
There are too many changes on this page to be displayed.
The amount of changes on this page would crash your brower.
You can still verify the content by downloading the package file manually.