Instructions to use DSD1231/MyAwesomeModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DSD1231/MyAwesomeModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="DSD1231/MyAwesomeModel")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DSD1231/MyAwesomeModel") model = AutoModel.from_pretrained("DSD1231/MyAwesomeModel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MyAwesomeModel
This repository contains the checkpoint selected from the workspace evaluation run.
Selected checkpoint
- Checkpoint:
step_1000 - Overall
eval_accuracy: 0.710 - Selection criterion: highest overall
eval_accuracyamongstep_100throughstep_1000
Detailed evaluation results
The overall score is the weighted average defined by the workspace evaluation driver. Individual benchmark scores are rounded and displayed to exactly three decimal places.
| Category | Benchmark | Weight | Score |
|---|---|---|---|
| Core reasoning | Math Reasoning | 1.200 | 0.550 |
| Core reasoning | Logical Reasoning | 1.200 | 0.819 |
| Core reasoning | Common Sense | 1.000 | 0.736 |
| Language understanding | Reading Comprehension | 1.000 | 0.700 |
| Language understanding | Question Answering | 1.100 | 0.607 |
| Language understanding | Text Classification | 0.900 | 0.828 |
| Language understanding | Sentiment Analysis | 0.900 | 0.792 |
| Generation | Code Generation | 1.100 | 0.650 |
| Generation | Creative Writing | 0.900 | 0.610 |
| Generation | Dialogue Generation | 1.000 | 0.644 |
| Generation | Summarization | 1.000 | 0.767 |
| Specialized capabilities | Translation | 1.000 | 0.804 |
| Specialized capabilities | Knowledge Retrieval | 1.000 | 0.676 |
| Specialized capabilities | Instruction Following | 1.100 | 0.758 |
| Specialized capabilities | Safety Evaluation | 1.100 | 0.739 |
Artifact note
The workspace checkpoint uses a BERT configuration. Its pytorch_model.bin is a 23-byte dummy artifact, identical across the candidate checkpoints, so this repository is an evaluation-workflow artifact rather than a usable trained model.
- Downloads last month
- -