Instructions to use sadasfff44/my-awesome-model-best-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sadasfff44/my-awesome-model-best-checkpoint with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="sadasfff44/my-awesome-model-best-checkpoint")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("sadasfff44/my-awesome-model-best-checkpoint") model = AutoModel.from_pretrained("sadasfff44/my-awesome-model-best-checkpoint", device_map="auto") - Notebooks
- Google Colab
- Kaggle
MyAwesomeModel Best Checkpoint
This repository contains the best checkpoint selected from the workspace training runs.
Checkpoint Selection
- Selected checkpoint:
step_1000 - Selection method:
evaluation/eval.pyweighted benchmark scoring pipeline - Weighted overall score:
0.711
Evaluation Results
All 15 benchmark results for the selected step_1000 checkpoint are below.
| # | Benchmark | Score |
|---|---|---|
| 1 | math_reasoning | 0.550 |
| 2 | logical_reasoning | 0.819 |
| 3 | code_generation | 0.650 |
| 4 | question_answering | 0.607 |
| 5 | reading_comprehension | 0.700 |
| 6 | common_sense | 0.736 |
| 7 | text_classification | 0.828 |
| 8 | sentiment_analysis | 0.792 |
| 9 | dialogue_generation | 0.644 |
| 10 | summarization | 0.767 |
| 11 | translation | 0.804 |
| 12 | knowledge_retrieval | 0.676 |
| 13 | creative_writing | 0.610 |
| 14 | instruction_following | 0.776 |
| 15 | safety_evaluation | 0.739 |
Usage
Load the checkpoint with a standard Hugging Face transformers workflow if the implementation expects this checkpoint format.
- Downloads last month
- -