Instructions to use asdafee34/MyAwesomeModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use asdafee34/MyAwesomeModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="asdafee34/MyAwesomeModel")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("asdafee34/MyAwesomeModel") model = AutoModel.from_pretrained("asdafee34/MyAwesomeModel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Document all 15 benchmark results to three decimal places
Browse files
README.md
CHANGED
|
@@ -39,6 +39,8 @@ Beyond its improved reasoning capabilities, this version also offers a reduced h
|
|
| 39 |
|
| 40 |
The checkpoint was selected strictly by comparing `eval_accuracy` for every checkpoint found in the workspace. `step_1000` had the highest value.
|
| 41 |
|
|
|
|
|
|
|
| 42 |
<div align="center">
|
| 43 |
|
| 44 |
| | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
|
|
|
|
| 39 |
|
| 40 |
The checkpoint was selected strictly by comparing `eval_accuracy` for every checkpoint found in the workspace. `step_1000` had the highest value.
|
| 41 |
|
| 42 |
+
The table below reports the selected checkpoint's detailed results for all 15 evaluation benchmarks. All scores are shown to three decimal places.
|
| 43 |
+
|
| 44 |
<div align="center">
|
| 45 |
|
| 46 |
| | Benchmark | Model1 | Model2 | Model1-v2 | MyAwesomeModel |
|