BAAI/bge-small-en-v1.5
A lightweight English text embedding model released by the Beijing Academy of Artificial Intelligence (BAAI). It outputs 384-dimensional vectors and is compact in size, suitable for CPU deployment.
Timeline (last 90 days)
Using the BAAI/bge-small-en-v1.5 model to generate 384-dimensional vectors, disk usage is about 33MB, running purely on CPU with no API key required.
BAAI/bge-small-en-v1.5 is an English general-purpose embedding model released by BAAI, with 384 dimensions, based on the BERT architecture, and a maximum sequence length of 512 tokens.
BAAI/bge-small-en-v1.5 uses a WordPiece tokenizer, which splits snake_case and camelCase into meaningless fragments.
The embedding model's maximum length means that inputs exceeding 512 tokens are silently truncated, so the example sets the chunk budget to 480 tokens.
cross-encoder/ms-marco-MiniLM-L6-v2 and BAAI/bge-small-en-v1.5 rank just behind the top spot on the Hugging Face download chart, with this week's downloads declining by approximately 5.6% and 4.0% respectively.
All Facts (5)
Using the BAAI/bge-small-en-v1.5 model to generate 384-dimensional vectors, disk usage is about 33MB, running purely on CPU with no API key required.
50%UnverifiedBAAI/bge-small-en-v1.5 is an English general-purpose embedding model released by BAAI, with 384 dimensions, based on the BERT architecture, and a maximum sequence length of 512 tokens.
50%UnverifiedBAAI/bge-small-en-v1.5 uses a WordPiece tokenizer, which splits snake_case and camelCase into meaningless fragments.
50%UnverifiedThe embedding model's maximum length means that inputs exceeding 512 tokens are silently truncated, so the example sets the chunk budget to 480 tokens.
50%Unverifiedcross-encoder/ms-marco-MiniLM-L6-v2 and BAAI/bge-small-en-v1.5 rank just behind the top spot on the Hugging Face download chart, with this week's downloads declining by approximately 5.6% and 4.0% respectively.
50%