Instructions to use thrunlab/loading_test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thrunlab/loading_test with Transformers:
# Load model directly from transformers import AutoTokenizer, SparseMistral tokenizer = AutoTokenizer.from_pretrained("thrunlab/loading_test") model = SparseMistral.from_pretrained("thrunlab/loading_test", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 111 Bytes
a95c374 | 1 2 3 4 5 6 7 | {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.2"
}
|