Sentence Similarity
sentence-transformers
Safetensors
Bengali
electra
retriever
bangla
bengali
retrieval
bert
Instructions to use SayedShaun/bangla-retriever with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use SayedShaun/bangla-retriever with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("SayedShaun/bangla-retriever") sentences = [ "সে একজন সুখী ব্যক্তি", "সে হ্যাপি কুকুর", "সে খুব সুখী মানুষ", "আজ একটি রৌদ্রোজ্জ্বল দিন" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from SayedShaun/bangla-retriever: direct link, hf CLI and curl.
- Browser
- Download file 480 Bytes
-
https://huggingface.co/SayedShaun/bangla-retriever/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://SayedShaun/bangla-retriever/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/SayedShaun/bangla-retriever/resolve/main/tokenizer_config.json
480 Bytes
| { | |
| "backend": "tokenizers", | |
| "cls_token": "[CLS]", | |
| "do_lower_case": false, | |
| "extra_special_tokens": [ | |
| "<classify>", | |
| "</classify>" | |
| ], | |
| "full_tokenizer_file": null, | |
| "is_local": false, | |
| "local_files_only": true, | |
| "mask_token": "[MASK]", | |
| "model_max_length": 1000000000000000019884624838656, | |
| "pad_token": "[PAD]", | |
| "sep_token": "[SEP]", | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": false, | |
| "tokenizer_class": "BertTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |