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

chat: Add Q8_0 quantization type

Browse Source
This commit is contained in:
Venkatesh Srinivas 2024-08-28 15:13:42 +00:00
parent e8d74d8bf4
commit fa48c33b70
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
gpt4all-chat/src/modellist.cpp
View File

@ -2005,6 +2005,7 @@ void ModelList::handleDiscoveryErrorOccurred(QNetworkReply::NetworkError code)
enum QuantType {
Q4_0 = 0,
Q4_1,
Q8_0,
F16,
F32,
Unknown
@ -2015,6 +2016,7 @@ QuantType toQuantType(const QString& filename)
QString lowerCaseFilename = filename.toLower();
if (lowerCaseFilename.contains("q4_0")) return Q4_0;
if (lowerCaseFilename.contains("q4_1")) return Q4_1;
if (lowerCaseFilename.contains("q8_0")) return Q8_0;
if (lowerCaseFilename.contains("f16")) return F16;
if (lowerCaseFilename.contains("f32")) return F32;
return Unknown;
@ -2025,6 +2027,7 @@ QString toQuantString(const QString& filename)
QString lowerCaseFilename = filename.toLower();
if (lowerCaseFilename.contains("q4_0")) return "q4_0";
if (lowerCaseFilename.contains("q4_1")) return "q4_1";
if (lowerCaseFilename.contains("q8_0")) return "q8_0";
if (lowerCaseFilename.contains("f16")) return "f16";
if (lowerCaseFilename.contains("f32")) return "f32";
return QString();