Instructions to use nirantk/splade-v3-lexical with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nirantk/splade-v3-lexical with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="nirantk/splade-v3-lexical")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("nirantk/splade-v3-lexical") model = AutoModelForMaskedLM.from_pretrained("nirantk/splade-v3-lexical", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model_args.json from nirantk/splade-v3-lexical: direct link, hf CLI and curl.
- Browser
- Download file 292 Bytes
-
https://huggingface.co/nirantk/splade-v3-lexical/resolve/refs%2Fpr%2F1/model_args.json
- Command line
-
hf download hf://nirantk/splade-v3-lexical@refs/pr/1/model_args.json
-
curl -L -o model_args.json https://huggingface.co/nirantk/splade-v3-lexical/resolve/refs%2Fpr%2F1/model_args.json
292 Bytes
| { | |
| "model_name_or_path": "naver/splade-cocondenser-selfdistil", | |
| "max_length": 128, | |
| "shared_weights": true, | |
| "splade_doc": false, | |
| "model_q": null, | |
| "dense_pooling": "cls", | |
| "dense": false, | |
| "adapter_name": null, | |
| "adapter_config": null, | |
| "load_adapter": null | |
| } |