Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions include/llama.h
Original file line number Diff line number Diff line change
Expand Up @@ -157,6 +157,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q1_0 = 40, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q2_0 = 41, // except 1d tensors
LLAMA_FTYPE_MOSTLY_PQ2_0 = 141, // except 1d tensors (Prism group-128 Q2_0; matches published PQ2_0 ggufs)
LLAMA_FTYPE_MOSTLY_PQ2_0_LEGACY = 142, // pre-rename value for the same format, still found in published ggufs

LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};
Expand Down
3 changes: 3 additions & 0 deletions src/llama-model-loader.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,9 @@ const char * llama_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_Q1_0: name = LLAMA_FTYPE_PREFIX "Q1_0"; break;
case LLAMA_FTYPE_MOSTLY_Q2_0: name = LLAMA_FTYPE_PREFIX "Q2_0"; break;
case LLAMA_FTYPE_MOSTLY_PQ2_0: name = LLAMA_FTYPE_PREFIX "PQ2_0 - 2.13 bpw (group 128)"; break;
// ggufs packed before the Q2_0_G128 -> PQ2_0 rename carry the old ftype value.
// They load and compute correctly; name it so it does not report as unknown.
case LLAMA_FTYPE_MOSTLY_PQ2_0_LEGACY: name = LLAMA_FTYPE_PREFIX "PQ2_0 - 2.13 bpw (group 128, legacy ftype)"; break;
case LLAMA_FTYPE_MOSTLY_Q4_0: name = LLAMA_FTYPE_PREFIX "Q4_0"; break;
case LLAMA_FTYPE_MOSTLY_Q4_1: name = LLAMA_FTYPE_PREFIX "Q4_1"; break;
case LLAMA_FTYPE_MOSTLY_Q5_0: name = LLAMA_FTYPE_PREFIX "Q5_0"; break;
Expand Down