From 740b17b4854f88ce92a3c6726702d6188c8f7bdd Mon Sep 17 00:00:00 2001
From: YuBai <byheaven0912@gmail.com>
Date: Tue, 10 Mar 2026 18:54:36 +0800
Subject: [PATCH] docs: fix Qwen3-Embedding GGUF filename case in README and
 llm.ts

HuggingFace filenames are case-sensitive. The documented filename
'qwen3-embedding-0.6b-q8_0.gguf' (lowercase) returns 404. The correct
filename is 'Qwen3-Embedding-0.6B-Q8_0.gguf' (original case from the
HuggingFace repo).

Co-Authored-By: Oz <oz-agent@warp.dev>
---
 README.md  | 2 +-
 src/llm.ts | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 2b72422..9d43ecf 100644
--- a/README.md
+++ b/README.md
@@ -341,7 +341,7 @@ This is useful for multilingual corpora (e.g. Chinese, Japanese, Korean) where
 
 ```sh
 # Use Qwen3-Embedding-0.6B for better multilingual (CJK) support
-export QMD_EMBED_MODEL="hf:Qwen/Qwen3-Embedding-0.6B-GGUF/qwen3-embedding-0.6b-q8_0.gguf"
+export QMD_EMBED_MODEL="hf:Qwen/Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf"
 
 # After changing the model, re-embed all collections:
 qmd embed -f
diff --git a/src/llm.ts b/src/llm.ts
index 100a1ec..1b9e426 100644
--- a/src/llm.ts
+++ b/src/llm.ts
@@ -192,7 +192,7 @@ export type RerankDocument = {
 
 // HuggingFace model URIs for node-llama-cpp
 // Format: hf:<user>/<repo>/<file>
-// Override via QMD_EMBED_MODEL env var (e.g. hf:Qwen/Qwen3-Embedding-0.6B-GGUF/qwen3-embedding-0.6b-q8_0.gguf)
+// Override via QMD_EMBED_MODEL env var (e.g. hf:Qwen/Qwen3-Embedding-0.6B-GGUF/Qwen3-Embedding-0.6B-Q8_0.gguf)
 const DEFAULT_EMBED_MODEL = process.env.QMD_EMBED_MODEL ?? "hf:ggml-org/embeddinggemma-300M-GGUF/embeddinggemma-300M-Q8_0.gguf";
 const DEFAULT_RERANK_MODEL = "hf:ggml-org/Qwen3-Reranker-0.6B-Q8_0-GGUF/qwen3-reranker-0.6b-q8_0.gguf";
 // const DEFAULT_GENERATE_MODEL = "hf:ggml-org/Qwen3-0.6B-GGUF/Qwen3-0.6B-Q8_0.gguf";