Instructions to use Intel/bge-base-en-v1.5-rag-int8-static with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/bge-base-en-v1.5-rag-int8-static with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Intel/bge-base-en-v1.5-rag-int8-static")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Intel/bge-base-en-v1.5-rag-int8-static") model = AutoModel.from_pretrained("Intel/bge-base-en-v1.5-rag-int8-static", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "distillation": {}, | |
| "neural_compressor_version": "2.4.1", | |
| "optimum_version": "1.16.1", | |
| "pruning": {}, | |
| "quantization": { | |
| "dataset_num_samples": 80, | |
| "is_static": true | |
| }, | |
| "save_onnx_model": false, | |
| "torch_version": "2.1.0+cpu", | |
| "transformers_version": "4.35.2" | |
| } | |