Instructions to use petra345/MyAwesomeModel-EfficientRelease-TestRepo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use petra345/MyAwesomeModel-EfficientRelease-TestRepo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="petra345/MyAwesomeModel-EfficientRelease-TestRepo")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("petra345/MyAwesomeModel-EfficientRelease-TestRepo") model = AutoModel.from_pretrained("petra345/MyAwesomeModel-EfficientRelease-TestRepo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "repo_name": "MyAwesomeModel-EfficientRelease-TestRepo", | |
| "selection_policy": "Choose the smallest numeric training step whose weighted overall score, safety_evaluation, and instruction_following meet their release thresholds.", | |
| "selected_checkpoint": "step_800", | |
| "thresholds": { | |
| "overall_min": 0.680, | |
| "safety_evaluation_min": 0.720, | |
| "instruction_following_min": 0.740 | |
| }, | |
| "checkpoint_scores": [ | |
| { | |
| "checkpoint": "step_100", | |
| "overall": 0.480, | |
| "safety_evaluation": 0.628, | |
| "instruction_following": 0.550 | |
| }, | |
| { | |
| "checkpoint": "step_200", | |
| "overall": 0.535, | |
| "safety_evaluation": 0.650, | |
| "instruction_following": 0.610 | |
| }, | |
| { | |
| "checkpoint": "step_300", | |
| "overall": 0.576, | |
| "safety_evaluation": 0.668, | |
| "instruction_following": 0.650 | |
| }, | |
| { | |
| "checkpoint": "step_400", | |
| "overall": 0.608, | |
| "safety_evaluation": 0.683, | |
| "instruction_following": 0.679 | |
| }, | |
| { | |
| "checkpoint": "step_500", | |
| "overall": 0.635, | |
| "safety_evaluation": 0.696, | |
| "instruction_following": 0.700 | |
| }, | |
| { | |
| "checkpoint": "step_600", | |
| "overall": 0.656, | |
| "safety_evaluation": 0.707, | |
| "instruction_following": 0.717 | |
| }, | |
| { | |
| "checkpoint": "step_700", | |
| "overall": 0.674, | |
| "safety_evaluation": 0.717, | |
| "instruction_following": 0.730 | |
| }, | |
| { | |
| "checkpoint": "step_800", | |
| "overall": 0.689, | |
| "safety_evaluation": 0.725, | |
| "instruction_following": 0.741 | |
| }, | |
| { | |
| "checkpoint": "step_900", | |
| "overall": 0.700, | |
| "safety_evaluation": 0.732, | |
| "instruction_following": 0.750 | |
| }, | |
| { | |
| "checkpoint": "step_1000", | |
| "overall": 0.710, | |
| "safety_evaluation": 0.739, | |
| "instruction_following": 0.758 | |
| } | |
| ], | |
| "gate_margins": [ | |
| { | |
| "checkpoint": "step_100", | |
| "overall_margin": -0.200, | |
| "safety_evaluation_margin": -0.092, | |
| "instruction_following_margin": -0.190, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_200", | |
| "overall_margin": -0.145, | |
| "safety_evaluation_margin": -0.070, | |
| "instruction_following_margin": -0.130, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_300", | |
| "overall_margin": -0.104, | |
| "safety_evaluation_margin": -0.052, | |
| "instruction_following_margin": -0.090, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_400", | |
| "overall_margin": -0.072, | |
| "safety_evaluation_margin": -0.037, | |
| "instruction_following_margin": -0.061, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_500", | |
| "overall_margin": -0.045, | |
| "safety_evaluation_margin": -0.024, | |
| "instruction_following_margin": -0.040, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_600", | |
| "overall_margin": -0.024, | |
| "safety_evaluation_margin": -0.013, | |
| "instruction_following_margin": -0.023, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_700", | |
| "overall_margin": -0.006, | |
| "safety_evaluation_margin": -0.003, | |
| "instruction_following_margin": -0.010, | |
| "meets_all_gates": false | |
| }, | |
| { | |
| "checkpoint": "step_800", | |
| "overall_margin": 0.009, | |
| "safety_evaluation_margin": 0.005, | |
| "instruction_following_margin": 0.001, | |
| "meets_all_gates": true | |
| }, | |
| { | |
| "checkpoint": "step_900", | |
| "overall_margin": 0.020, | |
| "safety_evaluation_margin": 0.012, | |
| "instruction_following_margin": 0.010, | |
| "meets_all_gates": true | |
| }, | |
| { | |
| "checkpoint": "step_1000", | |
| "overall_margin": 0.030, | |
| "safety_evaluation_margin": 0.019, | |
| "instruction_following_margin": 0.018, | |
| "meets_all_gates": true | |
| } | |
| ], | |
| "selected_benchmark_scores": { | |
| "math_reasoning": 0.522, | |
| "logical_reasoning": 0.773, | |
| "common_sense": 0.717, | |
| "reading_comprehension": 0.677, | |
| "question_answering": 0.593, | |
| "text_classification": 0.809, | |
| "sentiment_analysis": 0.780, | |
| "code_generation": 0.619, | |
| "creative_writing": 0.577, | |
| "dialogue_generation": 0.624, | |
| "summarization": 0.750, | |
| "translation": 0.795, | |
| "knowledge_retrieval": 0.662, | |
| "instruction_following": 0.741, | |
| "safety_evaluation": 0.725 | |
| }, | |
| "artifact_manifest": [ | |
| { | |
| "path": "README.md", | |
| "sha256": "3e0876deafb0fe0e1ece7efb7bfc1ae5092bab1bb601e108c10c4ff3ab1152e0" | |
| }, | |
| { | |
| "path": "config.json", | |
| "sha256": "7087b54618ddc9cd146c068edaae90d07ca5227b4a0d9bdc9f54e3c03d4dcd39" | |
| }, | |
| { | |
| "path": "figures/fig1.png", | |
| "sha256": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a" | |
| }, | |
| { | |
| "path": "figures/fig2.png", | |
| "sha256": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a" | |
| }, | |
| { | |
| "path": "figures/fig3.png", | |
| "sha256": "bd81e62dbd4289b54d154db29f00e5854d7b6c1f7acdc0d8f6647f790567b43a" | |
| }, | |
| { | |
| "path": "pytorch_model.bin", | |
| "sha256": "965362299a238de576a92dfdd3e32aea7a2bacc94b2c41541c8c9258b923f587" | |
| } | |
| ], | |
| "readback_verified": true | |
| } | |