mpt: allow q4_2 quantized models to load

1 year ago · 5002614b20
parent 832720dd27
commit 5002614b20
1 changed files with 1 additions and 0 deletions
--- a/llmodel/mpt.cpp
+++ b/llmodel/mpt.cpp
@ -236,6 +236,7 @@ bool mpt_model_load(const std::string &fname, std::istream &fin, mpt_model & mod
        case 1: wtype = GGML_TYPE_F16;  break;
        case 2: wtype = GGML_TYPE_Q4_0; break;
        case 3: wtype = GGML_TYPE_Q4_1; break;
+        case 5: wtype = GGML_TYPE_Q4_2; break;
        default:
                {
                    fprintf(stderr, "%s: invalid model file '%s' (bad f16 value %d)\n",