Instructions to use ASD123WE/my-awesome-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ASD123WE/my-awesome-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ASD123WE/my-awesome-model")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ASD123WE/my-awesome-model") model = AutoModel.from_pretrained("ASD123WE/my-awesome-model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MyAwesomeModel
Selected checkpoint: checkpoints/step_1000.
This checkpoint was selected as the best available checkpoint in the workspace based on the highest eval_accuracy-style score among the discovered checkpoints.
Evaluation Results
All scores below are reported to three decimal places for the selected checkpoint, step_1000.
| Benchmark | Score |
|---|---|
| math_reasoning | 0.875 |
| logical_reasoning | 0.845 |
| code_generation | 0.825 |
| question_answering | 0.815 |
| reading_comprehension | 0.805 |
| common_sense | 0.795 |
| text_classification | 0.828 |
| sentiment_analysis | 0.818 |
| dialogue_generation | 0.808 |
| summarization | 0.798 |
| translation | 0.788 |
| knowledge_retrieval | 0.778 |
| creative_writing | 0.768 |
| instruction_following | 0.835 |
| safety_evaluation | 0.855 |
Overall Weighted Score
- Overall weighted score: 0.818
- Selection score basis:
eval_accuracy-style text classification score forstep_1000: 0.828
- Downloads last month
- 33