Card: what to do when a --from-huggingface-repo download is cut short
Browse files
README.md
CHANGED
|
@@ -66,6 +66,8 @@ litert-lm run --from-huggingface-repo=mlboydaisuke/MiniCPM5-2B-LiteRT MiniCPM5-2
|
|
| 66 |
litert-lm run ./MiniCPM5-2B_int4.litertlm --backend gpu --cache no --prompt "..."
|
| 67 |
```
|
| 68 |
|
|
|
|
|
|
|
| 69 |
On Android the files import into the [Google AI Edge Gallery](https://github.com/google-ai-edge/gallery) app ("Import from HF" with this repo's file URL, or a local file).
|
| 70 |
|
| 71 |
Since the 2026-10-13 re-pack the default is a **direct answer**: the bundled template closes an empty think block unless `enable_thinking` is true (before, the model decided for itself and in practice reasoned before every answer). With thinking on:
|
|
|
|
| 66 |
litert-lm run ./MiniCPM5-2B_int4.litertlm --backend gpu --cache no --prompt "..."
|
| 67 |
```
|
| 68 |
|
| 69 |
+
If `run` stops right after the download with no error message from the CLI (a bus error; exit status 138 on a Mac) or with an error log that contains `too large for file size`, the downloaded file may be incomplete. The litert-lm CLI (0.14.0 to 0.19.2, and litert-lm-nightly 0.20.0.dev20261112) can keep an incomplete download in `~/.litert-lm/cache/huggingface/mlboydaisuke/MiniCPM5-2B-LiteRT/` and uses it again on later runs without checking its size. Delete that file and run the command again.
|
| 70 |
+
|
| 71 |
On Android the files import into the [Google AI Edge Gallery](https://github.com/google-ai-edge/gallery) app ("Import from HF" with this repo's file URL, or a local file).
|
| 72 |
|
| 73 |
Since the 2026-10-13 re-pack the default is a **direct answer**: the bundled template closes an empty think block unless `enable_thinking` is true (before, the model decided for itself and in practice reasoned before every answer). With thinking on:
|