Instructions to use petra345/MyAwesomeModel-CompactRepo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use petra345/MyAwesomeModel-CompactRepo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="petra345/MyAwesomeModel-CompactRepo")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("petra345/MyAwesomeModel-CompactRepo") model = AutoModel.from_pretrained("petra345/MyAwesomeModel-CompactRepo") - Notebooks
- Google Colab
- Kaggle
| { | |
| "scorecard_sha256": "91f300eaa4514b60fe2bbae017ca263ddf4b646ef51d003a692bbadad7912678", | |
| "top_three_checkpoints": [ | |
| { | |
| "rank": 1, | |
| "checkpoint": "step_1000", | |
| "weighted_overall_score": 0.710 | |
| }, | |
| { | |
| "rank": 2, | |
| "checkpoint": "step_900", | |
| "weighted_overall_score": 0.700 | |
| }, | |
| { | |
| "rank": 3, | |
| "checkpoint": "step_800", | |
| "weighted_overall_score": 0.689 | |
| } | |
| ], | |
| "per_benchmark_winners": { | |
| "math_reasoning": { | |
| "checkpoint": "step_1000", | |
| "score": 0.550 | |
| }, | |
| "code_generation": { | |
| "checkpoint": "step_1000", | |
| "score": 0.650 | |
| }, | |
| "text_classification": { | |
| "checkpoint": "step_1000", | |
| "score": 0.828 | |
| }, | |
| "sentiment_analysis": { | |
| "checkpoint": "step_1000", | |
| "score": 0.792 | |
| }, | |
| "question_answering": { | |
| "checkpoint": "step_1000", | |
| "score": 0.607 | |
| }, | |
| "logical_reasoning": { | |
| "checkpoint": "step_1000", | |
| "score": 0.819 | |
| }, | |
| "common_sense": { | |
| "checkpoint": "step_1000", | |
| "score": 0.736 | |
| }, | |
| "reading_comprehension": { | |
| "checkpoint": "step_1000", | |
| "score": 0.700 | |
| }, | |
| "dialogue_generation": { | |
| "checkpoint": "step_1000", | |
| "score": 0.644 | |
| }, | |
| "summarization": { | |
| "checkpoint": "step_1000", | |
| "score": 0.767 | |
| }, | |
| "translation": { | |
| "checkpoint": "step_1000", | |
| "score": 0.804 | |
| }, | |
| "knowledge_retrieval": { | |
| "checkpoint": "step_1000", | |
| "score": 0.676 | |
| }, | |
| "creative_writing": { | |
| "checkpoint": "step_1000", | |
| "score": 0.610 | |
| }, | |
| "instruction_following": { | |
| "checkpoint": "step_1000", | |
| "score": 0.758 | |
| }, | |
| "safety_evaluation": { | |
| "checkpoint": "step_1000", | |
| "score": 0.739 | |
| } | |
| }, | |
| "largest_adjacent_weighted_gain": { | |
| "from_checkpoint": "step_100", | |
| "to_checkpoint": "step_200", | |
| "weighted_score_gain": 0.055 | |
| }, | |
| "scorecard_row_count": 10 | |
| } | |