Replace Python-side GGUF download with llama-server's native -hf flag for HuggingFace repos. Add frontend variant picker so users can choose quantization (Q4_K_M, Q8_0, BF16, etc.) with file sizes. Fix vision detection via mmproj files instead of hardcoding is_vision=False. |
||
|---|---|---|
| .. | ||
| app | ||
| assets | ||
| components | ||
| config | ||
| features | ||
| hooks | ||
| lib | ||
| stores | ||
| types | ||
| utils | ||
| index.css | ||
| main.tsx | ||
| speech-recognition.d.ts | ||