加载中…
加载中…
A Model2Vec static embedding model distilled from intfloat/multilingual-e5-small (118M params), pruned to European languages only.
Pruned 36.5% of tokens (removed CJK, Arabic, Hebrew, Thai, Devanagari, Korean, Japanese, etc.).
| Before pruning | After pruning | |
|---|---|---|
| Vocabulary | 249,999 tokens | 158,843 tokens |
| Embedding dim | 256 | 256 |
from model2vec import StaticModel
model = StaticModel.from_pretrained("flipbitsnotburgers/m2v-e5-small-european")
embeddings = model.encode(["deodorant", "Duschgel", "shower gel"])
MIT (same as base model)