Model reference · open weights
sentence-croissant-llm is an open-weight embedding model from Wissam42. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | Wissam42 |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 2k tokens |
| Runs with | sentence-transformers |
| Released | 2024-02-07 |
| Popularity | 4k downloads / month |
| Licence | Open weights |
About
The model sentence-croissant-llm-base is designed to generate French text embeddings. It has been fine-tuned using the very recent pre-trained LLM croissantllm/CroissantLLMBase with the strategy of Siamese-BERT implemented in the library 'sentences-transformers'. The fine tuning dataset used is the French training split of stsb.
Using this model becomes easy when you have sentence-transformers installed:
pip install -U sentence-transformers
Then you can use the model like this:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("Wissam42/sentence-croissant-llm-base")
sentences = ["Le chat mange la souris", "Un felin devore un rongeur", "Je travaille sur un ordinateur", "Je developpe sur mon pc"]
embeddings = model.encode(sentences)
print(embeddings)
@article{faysse2024croissantllm,
title={CroissantLLM: A Truly Bilingual French-English Language Model},
author={Faysse, Manuel and Fernandes, Patrick and Guerreiro, Nuno and Loison, Ant{\'o}nio and Alves, Duarte and Corro, Caio and Boizard, Nicolas and Alves, Jo{\~a}o and Rei, Ricardo and Martins, Pedro and others},
journal={arXiv preprint arXiv:2402.00786},
year={2024}
}
@article{reimers2019sentence,
title={Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
author={Nils Reimers, Iryna Gurevych},
journal={https://arxiv.org/abs/1908.10084},
year={2019}
}From the published model card. Full card on the HuggingFace links in the sidebar.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Sentence-Embedding | Text Similarity fr | Test Pearson correlation coefficient |
Using it via the API
Once AxForge deploys sentence-croissant-llm for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sentence-croissant-llm below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"sentence-croissant-llm","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.