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

Merge pull request #38 from odysseus0/fix/readme-model-sizes

Browse Source 
docs: fix query expansion model size (Qwen3-1.7B, not 0.6B)
This commit is contained in:
Tobias Lütke 2026-01-20 10:25:28 -04:00 committed by GitHub
commit 5b1671d2f6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -112,7 +112,7 @@ Although the tool works perfectly fine when you just tell your agent to use it o
▼ ▼
┌────────────────┐ ┌────────────────┐
│ Query Expansion│ │ Original Query│
│ (Qwen3-0.6B) │ │ (×2 weight) │
│ (Qwen3-1.7B) │ │ (×2 weight) │
└───────┬────────┘ └───────┬────────┘
│ │
│ 2 alternative queries │
@ -213,7 +213,7 @@ QMD uses three local GGUF models (auto-downloaded on first use):
|-------|---------|------|
| `embeddinggemma-300M-Q8_0` | Vector embeddings | ~300MB |
| `qwen3-reranker-0.6b-q8_0` | Re-ranking | ~640MB |
| `Qwen3-0.6B-Q8_0` | Query expansion | ~640MB |
| `Qwen3-1.7B-Q8_0` | Query expansion | ~2.2GB |
Models are downloaded from HuggingFace and cached in `~/.cache/qmd/models/`.
@ -515,7 +515,7 @@ Models are configured in `src/llm.ts` as HuggingFace URIs:
```typescript
const DEFAULT_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";
const DEFAULT_GENERATE_MODEL = "hf:ggml-org/Qwen3-1.7B-GGUF/Qwen3-1.7B-Q8_0.gguf";
```
### EmbeddingGemma Prompt Format