llm install_error ai_generated true

error: 加载模型失败：GGUF版本不兼容：模型版本为3，但llama.cpp仅支持版本2

error: failed to load model: incompatible GGUF version: model version is 3, but llama.cpp supports version 2

ID: llm/llamacpp-gguf-version-mismatch

其他格式: JSON · Markdown 中文 · English
95%修复率
90%置信度
1证据数
2023-11-20首次发现

版本兼容性

版本状态引入弃用备注
llama.cpp 2023-10-01 active — — —
llama.cpp 2023-12-15 active — — —
llama.cpp 2024-01-10 active — — —
GGUF v2 active — — —
GGUF v3 active — — —

根因分析

GGUF模型文件使用的GGUF格式版本（例如v3）比已安装的llama.cpp构建所支持的版本（例如v2）更新，原因是llama.cpp二进制文件过时。

English

GGUF model file was created with a newer version of the GGUF format (e.g., v3) than what the installed llama.cpp build supports (e.g., v2), due to outdated llama.cpp binaries.

generic

官方文档

https://github.com/ggerganov/llama.cpp#build

解决方案

  1. 通过从源代码重新构建，将llama.cpp更新到最新版本：

git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make clean && make -j
./main -m model.gguf
  2. 使用GitHub最新版本发布的预构建二进制文件：

wget https://github.com/ggerganov/llama.cpp/releases/latest/download/llama.cpp-main-ubuntu-x64.tar.gz
tar -xzf llama.cpp-main-ubuntu-x64.tar.gz
./main -m model.gguf

无效尝试

常见但无效的做法:

  1. 60% 失败

    Downgrading may lose metadata or quantization information; converters often produce corrupted files when going backward.

  2. 90% 失败

    Breaks file integrity checks and causes undefined behavior or crashes during model loading.