aboutsummaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
authorOnur Gündüz <ogunduz@gmail.com>2026-06-14 16:20:52 +0200
committerOnur Gündüz <ogunduz@gmail.com>2026-06-14 16:41:53 +0200
commit067ba8cc5673896f7c09866d0b9587ff7fe4b9f7 (patch)
tree7f4cbbbea949d865ad45dad33476b851923e61c0 /README.md
parentcb1f049e710cf8704ae29811b3058142c7f64840 (diff)
downloadffwd-067ba8cc5673896f7c09866d0b9587ff7fe4b9f7.tar.gz
ffwd-067ba8cc5673896f7c09866d0b9587ff7fe4b9f7.zip
server: add Qwen3-Embedding-8B model slot
Diffstat (limited to 'README.md')
-rw-r--r--README.md4
1 files changed, 2 insertions, 2 deletions
diff --git a/README.md b/README.md
index f056d40..8427674 100644
--- a/README.md
+++ b/README.md
@@ -83,8 +83,8 @@ Late-interaction reranking endpoint:
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.
+`Qwen3-Embedding-4B`, 4096 for `Qwen3-Embedding-8B`). Truncated Matryoshka
+embeddings are re-normalized before encoding.
Example: