leehwui 6426b73a5e fix: export only required models instead of entire Ollama directory ...

- Changed export-ollama-models.sh to selectively copy only qwen3:14b and qwen3-embedding:4b
- Parses manifest files to identify required blob files
- Significantly reduces Docker image size by excluding unrelated models
- Added summary showing which models were skipped

This prevents accidentally including other models (like deepseek-r1, bge-m3, etc.)
that may exist in the user's Ollama directory but are not needed for the project.

2025-12-08 12:00:11 +08:00

5.1 KiB

Executable File

Raw Blame History

View Raw