Instructions to use castorini/tct_colbert-v2-msmarco-cqe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use castorini/tct_colbert-v2-msmarco-cqe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="castorini/tct_colbert-v2-msmarco-cqe")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("castorini/tct_colbert-v2-msmarco-cqe") model = AutoModel.from_pretrained("castorini/tct_colbert-v2-msmarco-cqe", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is to reproduce Contextualized Query Embeddings for Conversational Search described in the following paper:
Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. Contextualized Query Embeddings for Conversational Search. EMNLP, Nov 2021.
This model is finetuend only on query ecoder with frezzed passage encoder. The starting point is the tct_colbert-msmarco. The detailed usage of the model will be out soon on Chatty Goose. You can also check the fine-tuning and inference using tensorflow in our CQE repo
- Downloads last month
- 6