vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-13 02:19:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

missed out gpt2

Browse source
This commit is contained in:
Concedo 2023-05-21 01:44:47 +08:00
parent 2ead735f08
commit 75e4548821
2 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
expose.cpp
View file

@ -103,7 +103,7 @@ extern "C"
return true; return true;
} }
} }
else if(file_format==FileFormat::GPT2_1||file_format==FileFormat::GPT2_2||file_format==FileFormat::GPT2_3) else if(file_format==FileFormat::GPT2_1||file_format==FileFormat::GPT2_2||file_format==FileFormat::GPT2_3||file_format==FileFormat::GPT2_4)
{ {
printf("\n---\nIdentified as GPT-2 model: (ver %d)\nAttempting to Load...\n---\n", file_format); printf("\n---\nIdentified as GPT-2 model: (ver %d)\nAttempting to Load...\n---\n", file_format);
ModelLoadResult lr = gpttype_load_model(inputs, file_format); ModelLoadResult lr = gpttype_load_model(inputs, file_format);
@ -141,7 +141,7 @@ extern "C"
return true; return true;
} }
} }
else if(file_format==FileFormat::NEOX_1 || file_format==FileFormat::NEOX_2 || file_format==FileFormat::NEOX_3 || file_format==FileFormat::NEOX_4 || file_format==FileFormat::NEOX_5|| file_format==FileFormat::NEOX_6|| file_format==FileFormat::NEOX_7) else if(file_format==FileFormat::NEOX_1 || file_format==FileFormat::NEOX_2 || file_format==FileFormat::NEOX_3 || file_format==FileFormat::NEOX_4 || file_format==FileFormat::NEOX_5 || file_format==FileFormat::NEOX_6 || file_format==FileFormat::NEOX_7)
{ {
printf("\n---\nIdentified as GPT-NEO-X model: (ver %d)\nAttempting to Load...\n---\n", file_format); printf("\n---\nIdentified as GPT-NEO-X model: (ver %d)\nAttempting to Load...\n---\n", file_format);
ModelLoadResult lr = gpttype_load_model(inputs, file_format); ModelLoadResult lr = gpttype_load_model(inputs, file_format);

1
otherarch/tools/gpt2_quantize.cpp
View file

@ -135,7 +135,6 @@ bool gpt2_model_quantize(const std::string & fname_inp, const std::string & fnam
// ./gpt-2-quantize models/gpt-2-117M/ggml-model.bin models/gpt-2-117M/ggml-model-quant.bin type // ./gpt-2-quantize models/gpt-2-117M/ggml-model.bin models/gpt-2-117M/ggml-model-quant.bin type
// //
int main(int argc, char ** argv) { int main(int argc, char ** argv) {
ggml_time_init();
if (argc != 4) { if (argc != 4) {
fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]); fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
ggml_print_ftypes(stderr); ggml_print_ftypes(stderr);