Instructions to use nvidia/dragon-multiturn-query-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nvidia/dragon-multiturn-query-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nvidia/dragon-multiturn-query-encoder")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("nvidia/dragon-multiturn-query-encoder") model = AutoModel.from_pretrained("nvidia/dragon-multiturn-query-encoder", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
|
Download evaluation/README.md from nvidia/dragon-multiturn-query-encoder: direct link, hf CLI and curl.
- Browser
- Download file 398 Bytes
-
https://huggingface.co/nvidia/dragon-multiturn-query-encoder/resolve/refs%2Fpr%2F6/evaluation/README.md
- Command line
-
hf download hf://nvidia/dragon-multiturn-query-encoder@refs/pr/6/evaluation/README.md
-
curl -L -o README.md https://huggingface.co/nvidia/dragon-multiturn-query-encoder/resolve/refs%2Fpr%2F6/evaluation/README.md
398 Bytes
| ### Commands for running evaluation | |
| ```console | |
| python evaluate.py --eval-dataset doc2dial | |
| python evaluate.py --eval-dataset quac | |
| python evaluate.py --eval-dataset qrecc | |
| ``` | |
| For the evaluations of topiocqa and inscit, the Wikipedia corpora need to be downloaded from their original repositories. | |
| - topiocqa: https://github.com/McGill-NLP/topiocqa | |
| - inscit: https://github.com/ellenmellon/INSCIT | |