ai-workspace-services/qmd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #349 from byheaven/fix/qwen3-embedding-model-filename-case

Browse Source 
docs: fix Qwen3-Embedding GGUF filename case (404 on download)
This commit is contained in:
Tobias Lütke 2026-03-10 20:08:53 -04:00 committed by GitHub
commit 55c951b15e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -500,7 +500,7 @@ 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

2
src/llm.ts
View File

@ -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";