Package: llama.cpp-tools
Version: 10108+dfsg1-1
Severity: normal
X-Debbugs-Cc: [email protected]
Dear Maintainer,
The model conversion script provided in /usr/share/doc now requires
additional Python scripts from upstream's conversion/ subdirectory.
Just running --help works, but a real conversion fails with:
/usr/bin/python3 /usr/share/doc/llama.cpp-tools/scripts/convert_hf_to_gguf.py \
\
--outtype bf16 \
--metadata ./metadata/metadata-override.json \
./safetensors/Qwen/Qwen3.5-0.8B \
--outfile ./bf16/qwen3.5-0.8b-bf16.gguf
Traceback (most recent call last):
File "/usr/share/doc/llama.cpp-tools/scripts/convert_hf_to_gguf.py", line 18,
in <module>
from conversion import (
...<8 lines>...
)
ModuleNotFoundError: No module named 'conversion'
We are working with [email protected] on solving this issue.
-- System Information:
Debian Release: forky/sid
APT prefers unstable
APT policy: (500, 'unstable')
Architecture: amd64 (x86_64)
Kernel: Linux 6.12.96+deb13-amd64 (SMP w/24 CPU threads; PREEMPT)
Kernel taint flags: TAINT_OOT_MODULE
Locale: LANG=C, LC_CTYPE=C.UTF-8 (charmap=UTF-8), LANGUAGE not set
Shell: /bin/sh linked to /usr/bin/dash
Init: unable to detect
Versions of packages llama.cpp-tools depends on:
ii debconf [debconf-2.0] 1.5.92
ii libc6 2.42-17
ii libgcc-s1 16.1.0-3
ii libggml0 0.17.0-1
ii libllama0 10108+dfsg1-1
ii libssl3t64 3.6.3-1
ii libstdc++6 16.1.0-3
ii systemd [systemd-tmpfiles] 261.2-1
ii wget 1.25.0-3
llama.cpp-tools recommends no packages.
Versions of packages llama.cpp-tools suggests:
pn llama.cpp-tools-webui-downloader <none>
-- debconf information:
llama.cpp-tools/default-ui: simplechat
llama.cpp-tools/path-error:
llama.cpp-tools/default-ui-custom-path:
