EmbeddingGemma 300M
Ceannasacht agus óstáil
Tá an tsamhail seo catalógaithe le haghaidh tagartha. Níl sí óstáilte ar LLM EU fós, agus ní fhreastalaíonn aon chríochphointe céadpháirtí uirthi anseo. Téann iarratais chuici chuig an soláthraí go díreach, faoi théarmaí an tsoláthraí sin féin.
Achoimre
EmbeddingGemma is a 308M-parameter text embedding model with a 768-dimensional output that can be truncated to 512, 256 or 128 dimensions through Matryoshka representation learning. The model card states a maximum input length of 2048 tokens and training data in over 100 spoken languages. It is released under Google’s Gemma terms rather than an OSI licence.
Sonraíochtaí
- Soláthraí
- Google DeepMind (US)
- Fuinneog chomhthéacs
- 2.0k
- Paraiméadair
- 0.3B
- Módúlachtaí
- embedding
- Ceadúnas
- gemma · licence
- Meáchain oscailte
- yes
- Dáta scaoilte
- 17 Iúil 2025
- Tascanna
- rag, multilingual-support, private, cheap
Teangacha
Láidir: en, de, fr, es, it, pt, nl, pl
Leordhóthanach: sv, da, fi, cs, ro, el, uk, ru, ar, hi, zh, ja, ko, tr
Teangacha
Láidir
- en
- de
- fr
- es
- it
- pt
- nl
- pl
Leordhóthanach
- sv
- da
- fi
- cs
- ro
- el
- uk
- ru
- ar
- hi
- zh
- ja
- ko
- tr
Gan fíorú: níl an t-éileamh seo doiciméadaithe ag an soláthraí. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.
Cathain a úsáidfear é
Láidreachtaí
- flexible output dimensions for cheaper vector indexes
- small enough to embed on CPU
- training data in over 100 languages
Teorainneacha
- 2048-token input limit
- Gemma terms of use, not an OSI-approved licence
- no retrieval benchmark has been run by LLM EU