github/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2025-09-22 20:10:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

server: do not process the system prompt twice for new models (#2924)

Browse Source 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
This commit is contained in:
Jared Van Bortel
2024-08-30 12:30:24 -04:00
committed by GitHub
parent 2f02cd407f
commit 813ccaf5d1
5 changed files with 21 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
gpt4all-chat/src/chat.cpp
View File

@@ -74,7 +74,6 @@ void Chat::connectLLM()
connect(this, &Chat::promptRequested, m_llmodel, &ChatLLM::prompt, Qt::QueuedConnection);
connect(this, &Chat::modelChangeRequested, m_llmodel, &ChatLLM::modelChangeRequested, Qt::QueuedConnection);
connect(this, &Chat::loadDefaultModelRequested, m_llmodel, &ChatLLM::loadDefaultModel, Qt::QueuedConnection);
connect(this, &Chat::loadModelRequested, m_llmodel, &ChatLLM::loadModel, Qt::QueuedConnection);
connect(this, &Chat::generateNameRequested, m_llmodel, &ChatLLM::generateName, Qt::QueuedConnection);
connect(this, &Chat::regenerateResponseRequested, m_llmodel, &ChatLLM::regenerateResponse, Qt::QueuedConnection);
connect(this, &Chat::resetResponseRequested, m_llmodel, &ChatLLM::resetResponse, Qt::QueuedConnection);

1
gpt4all-chat/src/chat.h
View File

@@ -146,7 +146,6 @@ Q_SIGNALS:
void modelInfoChanged();
void restoringFromTextChanged();
void loadDefaultModelRequested();
void loadModelRequested(const ModelInfo &modelInfo);
void generateNameRequested();
void modelLoadingErrorChanged();
void isServerChanged();

21
gpt4all-chat/src/chatllm.cpp
View File

@@ -249,9 +249,11 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
// and what the type and name of that model is. I've tried to comment extensively in this method
// to provide an overview of what we're doing here.
// We're already loaded with this model
if (isModelLoaded() && this->modelInfo() == modelInfo)
return true;
if (isModelLoaded() && this->modelInfo() == modelInfo) {
// already acquired -> keep it and reset
resetContext();
return true; // already loaded
}
// reset status
emit modelLoadingPercentageChanged(std::numeric_limits<float>::min()); // small non-zero positive value
@@ -659,20 +661,25 @@ void ChatLLM::setModelInfo(const ModelInfo &modelInfo)
emit modelInfoChanged(modelInfo);
}
void ChatLLM::acquireModel() {
void ChatLLM::acquireModel()
{
m_llModelInfo = LLModelStore::globalInstance()->acquireModel();
emit loadedModelInfoChanged();
}
void ChatLLM::resetModel() {
void ChatLLM::resetModel()
{
m_llModelInfo = {};
emit loadedModelInfoChanged();
}
void ChatLLM::modelChangeRequested(const ModelInfo &modelInfo)
{
m_shouldBeLoaded = true;
loadModel(modelInfo);
// ignore attempts to switch to the same model twice
if (!isModelLoaded() || this->modelInfo() != modelInfo) {
m_shouldBeLoaded = true;
loadModel(modelInfo);
}
}
bool ChatLLM::handlePrompt(int32_t token)

8
gpt4all-chat/src/server.cpp
View File

@@ -361,14 +361,14 @@ QHttpServerResponse Server::handleCompletionRequest(const QHttpServerRequest &re
if (modelInfo.filename().isEmpty()) {
std::cerr << "ERROR: couldn't load default model " << modelRequested.toStdString() << std::endl;
return QHttpServerResponse(QHttpServerResponder::StatusCode::BadRequest);
} else if (!loadModel(modelInfo)) {
}
// NB: this resets the context, regardless of whether this model is already loaded
if (!loadModel(modelInfo)) {
std::cerr << "ERROR: couldn't load model " << modelInfo.name().toStdString() << std::endl;
return QHttpServerResponse(QHttpServerResponder::StatusCode::InternalServerError);
}
// don't remember any context
resetContext();
const QString promptTemplate = modelInfo.promptTemplate();
const float top_k = modelInfo.topK();
const int n_batch = modelInfo.promptBatchSize();