Octen-Embedding-4B-MLX-4bit / estha_embedding_config.json
davied-he's picture
Add official MLX-LM 4-bit conversion
99feffd verified
Raw
History Blame Contribute Delete
207 Bytes
{
"version": 1,
"pooling": "last_token",
"normalize": true,
"query_prefix": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
"document_prefix": " "
}