mirror of
https://github.com/nomic-ai/gpt4all.git
synced 2024-09-11 13:25:35 +03:00
embllm: fix use of llama ctx before loading (#2465)
This fixes a regression in PR #2396. Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
parent
9273b49b62
commit
1a00882276
@ -84,10 +84,6 @@ bool EmbeddingLLMWorker::loadModel()
|
||||
return false;
|
||||
}
|
||||
|
||||
// FIXME(jared): the user may want this to take effect without having to restart
|
||||
int n_threads = MySettings::globalInstance()->threadCount();
|
||||
m_model->setThreadCount(n_threads);
|
||||
|
||||
// NOTE: explicitly loads model on CPU to avoid GPU OOM
|
||||
// TODO(cebtenzzre): support GPU-accelerated embeddings
|
||||
bool success = m_model->loadModel(filePath.toStdString(), 2048, 0);
|
||||
@ -104,6 +100,11 @@ bool EmbeddingLLMWorker::loadModel()
|
||||
m_model = nullptr;
|
||||
return false;
|
||||
}
|
||||
|
||||
// FIXME(jared): the user may want this to take effect without having to restart
|
||||
int n_threads = MySettings::globalInstance()->threadCount();
|
||||
m_model->setThreadCount(n_threads);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user