Sentence Similarity
Transformers
PyTorch
ONNX
Safetensors
xlm-roberta
feature-extraction
language
granite
embeddings
multilingual
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use ibm-granite/granite-embedding-107m-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-embedding-107m-multilingual with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ibm-granite/granite-embedding-107m-multilingual") model = AutoModel.from_pretrained("ibm-granite/granite-embedding-107m-multilingual", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Download tokenizer_config.json from ibm-granite/granite-embedding-107m-multilingual: direct link, hf CLI and curl.
- Browser
- Download file 462 Bytes
-
https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://ibm-granite/granite-embedding-107m-multilingual/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/ibm-granite/granite-embedding-107m-multilingual/resolve/main/tokenizer_config.json
462 Bytes
| {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "granite-embedding-107m-multilingual", "sp_model_kwargs": {}, "special_tokens_map_file": "special_tokens_map.json", "tokenizer_class": "XLMRobertaTokenizer"} | |