Instructions to use dongbobo/my-demo-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dongbobo/my-demo-model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="dongbobo/my-demo-model") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("dongbobo/my-demo-model", dtype="auto") - Notebooks
- Google Colab
- Kaggle
MyModel
A demonstration model repository with a complete folder structure.
Architecture
The overall model architecture is illustrated below:
Results
Quantitative evaluation results on the benchmark suite:
Full numerical results are available in artifacts/report/table.csv.
Checkpoints
| File | Description |
|---|---|
config.json |
Model configuration |
model.safetensors |
Trained weights (fp32) |
tokenizer_config.json |
Tokenizer settings |
special_tokens_map.json |
Special token mappings |
Usage
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("dongbobo/my-demo-model")
tokenizer = AutoTokenizer.from_pretrained("dongbobo/my-demo-model")
Citation
@misc{mymodel2024,
author = {dongbobo},
title = {MyModel: A Demonstration Repository},
year = {2024}
}
- Downloads last month
- 15

