Embedding model

gte-Qwen2-1.5B-instruct

Qwen2-based multilingual GTE embedding model for retrieval, clustering, classification, and semantic similarity tasks. Token IDs on this page use the shared Qwen2 tokenizer vocabulary.

Alibaba

Endpoint

Embeddings

Status

Current

Default dimensions

1,536

Max input

32,000 tokens

Tokenizer

qwen2

Tokenizer tokens

151,646 known tokens (151,643 mergeable)

Open model token IDs Open tokenizer reference Model card