Instructions to use OpenMatch/t5-ance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMatch/t5-ance with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="OpenMatch/t5-ance")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("OpenMatch/t5-ance") model = AutoModel.from_pretrained("OpenMatch/t5-ance", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: mit | |
| # T5-ANCE | |
| T5-ANCE generally follows the training procedure described in [this page](https://openmatch.readthedocs.io/en/latest/dr-msmarco-passage.html), but uses a much larger batch size. | |
| Dataset used for training: | |
| - MS MARCO Passage | |
| Evaluation result: | |
| |Dataset|Metric|Result| | |
| |---|---|---| | |
| |MS MARCO Passage (dev) | MRR@10 | 0.3570| | |
| Important hyper-parameters: | |
| |Name|Value| | |
| |---|---| | |
| |Global batch size|256| | |
| |Learning rate|5e-6| | |
| |Maximum length of query|32| | |
| |Maximum length of document|128| | |
| |Template for query|`<text>`| | |
| |Template for document|`Title: <title> Text: <text>`| | |
| ### Paper | |
| \- |