Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
modernbert
feature-extraction
embeddings
Eval Results (legacy)
text-embeddings-inference
Instructions to use mjbommar/ogbert-110m-sentence with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use mjbommar/ogbert-110m-sentence with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("mjbommar/ogbert-110m-sentence") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use mjbommar/ogbert-110m-sentence with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("mjbommar/ogbert-110m-sentence") model = AutoModel.from_pretrained("mjbommar/ogbert-110m-sentence", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "additional_special_tokens": null, | |
| "backend": "tokenizers", | |
| "bos_token": "<|start|>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<|cls|>", | |
| "eos_token": "<|end|>", | |
| "extra_special_tokens": [], | |
| "is_local": false, | |
| "mask_token": "<|mask|>", | |
| "model_max_length": 1024, | |
| "model_type": "modernbert", | |
| "pad_token": "<|pad|>", | |
| "sep_token": "<|sep|>", | |
| "tokenizer_class": "TokenizersBackend", | |
| "unk_token": "<|unk|>", | |
| "vocab_size": 32767 | |
| } | |