Instructions to use McGill-NLP/dpr-statcan-conversation_encoder-title with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use McGill-NLP/dpr-statcan-conversation_encoder-title with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="McGill-NLP/dpr-statcan-conversation_encoder-title")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("McGill-NLP/dpr-statcan-conversation_encoder-title") model = AutoModel.from_pretrained("McGill-NLP/dpr-statcan-conversation_encoder-title", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from McGill-NLP/dpr-statcan-conversation_encoder-title: direct link, hf CLI and curl.
- Browser
- Download file 665 Bytes
-
https://huggingface.co/McGill-NLP/dpr-statcan-conversation_encoder-title/resolve/main/config.json
- Command line
-
hf download hf://McGill-NLP/dpr-statcan-conversation_encoder-title/config.json
-
curl -L -o config.json https://huggingface.co/McGill-NLP/dpr-statcan-conversation_encoder-title/resolve/main/config.json
665 Bytes
| { | |
| "_name_or_path": "facebook/dpr-question_encoder-single-nq-base", | |
| "architectures": [ | |
| "DPRQuestionEncoder" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "dpr", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "projection_dim": 0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.11.3", | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522 | |
| } | |