Instructions to use Sashavav/rag-resource-allocator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sashavav/rag-resource-allocator with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Sashavav/rag-resource-allocator", trust_remote_code=True) model = AutoModel.from_pretrained("Sashavav/rag-resource-allocator", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_model_dir": "/home/Sashavav/git/mef_models/models/jina_reranker", | |
| "hf_model_id": null, | |
| "tokenizer_source": null, | |
| "output_dir": "outputs/base/final", | |
| "onnx_path": "outputs/base/final/model.onnx", | |
| "opset": 18, | |
| "model_class": "JinaForRanking", | |
| "loaded_from_hub": false | |
| } |