AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fixes https://github.com/nomic-ai/gpt4all/issues/1760 LLModel ERROR: Could not find CPU LLaMA implementation.

Browse Source 
Inspired by Microsoft docs for LoadLibraryExA (https://learn.microsoft.com/en-us/windows/win32/api/libloaderapi/nf-libloaderapi-loadlibraryexa).
When using LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR, the lpFileName parameter must specify a fully qualified path, also it needs to be backslashes (\), not forward slashes (/).
This commit is contained in:
ThiloteE 2023-12-29 23:57:46 +01:00 committed by AT
parent 3e99b90c0b
commit 38d81c14d0
2 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
gpt4all-backend/dlhandle.h
View File

@ -54,6 +54,7 @@ public:
};
#else
#include <string>
#include <algorithm>
#include <exception>
#include <stdexcept>
#ifndef NOMINMAX
@ -75,7 +76,9 @@ public:
Dlhandle() : chandle(nullptr) {}
Dlhandle(const std::string& fpath) {
chandle = LoadLibraryExA(fpath.c_str(), NULL, LOAD_LIBRARY_SEARCH_DEFAULT_DIRS | LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR);
std::string path = fpath;
std::replace(path.begin(), path.end(), '/', '\\');
chandle = LoadLibraryExA(path.c_str(), NULL, LOAD_LIBRARY_SEARCH_DEFAULT_DIRS | LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR);
if (!chandle) {
throw Exception("dlopen(\""+fpath+"\"): Error");
}

2
gpt4all-backend/llmodel.cpp
View File

@ -104,7 +104,7 @@ const std::vector<LLModel::Implementation> &LLModel::Implementation::implementat
// Add to list if model implementation
try {
Dlhandle dl(p.string());
Dlhandle dl(std::filesystem::absolute(p).string());
if (!Implementation::isImplementation(dl)) {
continue;
}