Instructions to use aswath86/neural-sparse-encoding-splare-multilingual-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use aswath86/neural-sparse-encoding-splare-multilingual-v1 with PEFT:
from peft import PeftModel from transformers import AutoModel base_model = AutoModel.from_pretrained("Qwen/Qwen3-1.7B-Base") model = PeftModel.from_pretrained(base_model, "aswath86/neural-sparse-encoding-splare-multilingual-v1") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from aswath86/neural-sparse-encoding-splare-multilingual-v1: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/aswath86/neural-sparse-encoding-splare-multilingual-v1/resolve/main/tokenizer.json
- Command line
-
hf download hf://aswath86/neural-sparse-encoding-splare-multilingual-v1/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/aswath86/neural-sparse-encoding-splare-multilingual-v1/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- a3d4f68bbc97a180d8a83de17c4de95d0e41ee26749d5a7d52957ae4f9371520
- Size of remote file:
- 11.4 MB
- SHA256:
- d2d310548368eec19cc832883eb1069de52b1945318588478a95ab61d00bd002
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.