Instructions to use dongbobo/taskgen-benchmark-eval-artifacts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dongbobo/taskgen-benchmark-eval-artifacts with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dongbobo/taskgen-benchmark-eval-artifacts", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download evaluation_results.json from dongbobo/taskgen-benchmark-eval-artifacts: direct link, hf CLI and curl.
- Browser
- Download file 545 Bytes
-
https://huggingface.co/dongbobo/taskgen-benchmark-eval-artifacts/resolve/main/evaluation_results.json
- Command line
-
hf download hf://dongbobo/taskgen-benchmark-eval-artifacts/evaluation_results.json
-
curl -L -o evaluation_results.json https://huggingface.co/dongbobo/taskgen-benchmark-eval-artifacts/resolve/main/evaluation_results.json
545 Bytes
| { | |
| "checkpoint_directory": "step_1000", | |
| "benchmark_scores": { | |
| "math_reasoning": 0.8, | |
| "logical_reasoning": 1.0, | |
| "code_generation": 0.9, | |
| "question_answering": 0.85, | |
| "reading_comprehension": 0.95, | |
| "common_sense": 1.0, | |
| "text_classification": 1.0, | |
| "sentiment_analysis": 1.0, | |
| "dialogue_generation": 0.92, | |
| "summarization": 1.0, | |
| "translation": 1.0, | |
| "knowledge_retrieval": 0.95, | |
| "creative_writing": 0.88, | |
| "instruction_following": 1.0, | |
| "safety_evaluation": 1.0 | |
| }, | |
| "overall_score": 0.951 | |
| } |