Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:225516
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Instructions to use 2ADT-Consulting/susu-sentence-encoder-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use 2ADT-Consulting/susu-sentence-encoder-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("2ADT-Consulting/susu-sentence-encoder-v1") sentences = [ "Il leur donna cet ordre: «Vous transmettrez ce message à mon seigneur Esaü: Voici ce que dit ton serviteur Jacob: J'ai séjourné chez Laban et j'y suis resté jusqu'à maintenant.", "I na fe nde to, i naxa gbata sigafe ra kiiti banxi, barima xa fe gbɛtɛ minima i mu naxan kolon, na nɔma i rayaagide i dɔxɔboore ya xɔri.", "Wo xa sɔɔrie luxi nɛ alɔ tugumi naxee na tɛtɛ fari gɛɛsɛgɛ, kɔnɔ soge na te, e tugan, e siga yire mixi mu dɛnnaxɛ kolon.", "A naxa a fala e bɛ, «Wo yi nan falama n marigi Esayu bɛ, ‹I xa konyi di Yaxuba naxɛ, N bara bu Laban xɔnyi han ya." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Add bilingual (fr/en-sus) sentence encoder fine-tuned with MNRL on paraphrase-multilingual-MiniLM-L12-v2
cdd2b74 verified | { | |
| "backend": "tokenizers", | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "do_lower_case": true, | |
| "eos_token": "</s>", | |
| "is_local": false, | |
| "mask_token": "<mask>", | |
| "max_length": 128, | |
| "model_max_length": 128, | |
| "pad_to_multiple_of": null, | |
| "pad_token": "<pad>", | |
| "pad_token_type_id": 0, | |
| "padding_side": "right", | |
| "sep_token": "</s>", | |
| "stride": 0, | |
| "strip_accents": null, | |
| "tokenize_chinese_chars": true, | |
| "tokenizer_class": "TokenizersBackend", | |
| "truncation_side": "right", | |
| "truncation_strategy": "longest_first", | |
| "unk_token": "<unk>" | |
| } | |