Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 736f0c8ac9
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
|
|
||
| ### Repository Configuration (for downloading) | ||
| - `QWEN_GGUF_REPO`: HuggingFace repo for Qwen models (default: `Qwen/Qwen2-VL-8B-Instruct-GGUF`) | ||
| - `QWEN_GGUF_REPO`: HuggingFace repo for Qwen models (default: `Qwen/Qwen2.5-VL-7B-Instruct-GGUF`) |
There was a problem hiding this comment.
The documented default for QWEN_GGUF_REPO now says Qwen/Qwen2.5-VL-7B-Instruct-GGUF, but the actual download logic defaults to ggml-org/Qwen2.5-VL-7B-Instruct-GGUF in helper-scripts/fetch-models.sh (line 13). This mismatch can cause users who rely on this doc to set an incorrect repo override and then fail or fetch unexpected artifacts when running the model download flow.
Useful? React with 👍 / 👎.
1 participant
Summary\n- align docs with current model/vector store config\n- fix typos and wording\n- add agent guide and food category README\n- add licensing notes in sources docs\n\n## Testing\n- not run (doc-only changes)