Instructions to use Tarka-AIR/Tarka-Embedding-350M-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Tarka-AIR/Tarka-Embedding-350M-V1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Tarka-AIR/Tarka-Embedding-350M-V1", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
license issue
hi, cool work and promising models/research. I hate to be this guy but the lfm2 models are released under a custom 'LFM Open License v1.0 ' which require derivative works to use this same license. this variant being an LFM2-350M derivative and listed as apache-2.0 is not possible/in violation (unless I am missing something).
In general: if model released with a restrictive (non apache-2.0/MIT) license, it is overwhelmingly likely that any and all derivative works must follow that license (otherwise... their custom license is pointless..)
I apologize for the mistake, and I’ll update the license to correctly reflect the LFM Open License v1.0.
Appreciate you taking the time to flag this.