Sentence Similarity
sentence-transformers
PyTorch
Transformers
Oriya
bert
feature-extraction
text-embeddings-inference
Instructions to use l3cube-pune/odia-sentence-bert-nli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use l3cube-pune/odia-sentence-bert-nli with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("l3cube-pune/odia-sentence-bert-nli") sentences = [ "লোকটি কুড়াল দিয়ে একটি গাছ কেটে ফেলল", "একজন লোক কুড়াল দিয়ে একটি গাছের নিচে চপ করে", "একজন লোক গিটার বাজছে", "একজন মহিলা ঘোড়ায় চড়ে" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use l3cube-pune/odia-sentence-bert-nli with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("l3cube-pune/odia-sentence-bert-nli") model = AutoModel.from_pretrained("l3cube-pune/odia-sentence-bert-nli", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from l3cube-pune/odia-sentence-bert-nli: direct link, hf CLI and curl.
- Browser
- Download file 516 Bytes
-
https://huggingface.co/l3cube-pune/odia-sentence-bert-nli/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://l3cube-pune/odia-sentence-bert-nli/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/l3cube-pune/odia-sentence-bert-nli/resolve/main/tokenizer_config.json
516 Bytes
| { | |
| "cls_token": "[CLS]", | |
| "do_basic_tokenize": true, | |
| "do_lower_case": false, | |
| "lowercase": false, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 512, | |
| "name_or_path": "l3cube-pune/odia-sentence-bert-nli/", | |
| "never_split": null, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "special_tokens_map_file": "/ebs_ds_share/raviraj.j/temp/models/muril-base-cased/special_tokens_map.json", | |
| "strip_accents": false, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |