diff options
| author | Onur Gündüz <ogunduz@gmail.com> | 2026-06-14 16:06:18 +0200 |
|---|---|---|
| committer | Onur Gündüz <ogunduz@gmail.com> | 2026-06-14 16:41:53 +0200 |
| commit | cb1f049e710cf8704ae29811b3058142c7f64840 (patch) | |
| tree | 85df308a574fbc3408cd88cd82471896337c8669 /README.md | |
| parent | bb41b40bf881a1c59ee0d6153bcb0bb2f7a0044b (diff) | |
| download | ffwd-cb1f049e710cf8704ae29811b3058142c7f64840.tar.gz ffwd-cb1f049e710cf8704ae29811b3058142c7f64840.zip | |
all: add Qwen3-Embedding-4B + fix terminal token
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 6 |
1 files changed, 4 insertions, 2 deletions
@@ -81,8 +81,10 @@ Late-interaction reranking endpoint: - `POST /v1/rerank` — late-interaction MaxSim reranking -For `Qwen3-Embedding-0.6B`, `/v1/embeddings` accepts `dimensions` from 32 -to 1024. Truncated Matryoshka embeddings are re-normalized before encoding. +For Qwen3-Embedding models, `/v1/embeddings` accepts `dimensions` from 32 up to +the model's output size (1024 for `Qwen3-Embedding-0.6B`, 2560 for +`Qwen3-Embedding-4B`). Truncated Matryoshka embeddings are re-normalized before +encoding. Example: |
