diff options
Diffstat (limited to 'src/llama.cpp')
| -rw-r--r-- | src/llama.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/llama.cpp b/src/llama.cpp index dca03ade..eb982125 100644 --- a/src/llama.cpp +++ b/src/llama.cpp @@ -3774,6 +3774,7 @@ struct llama_model_loader { case GGML_TYPE_Q4_1: ftype = LLAMA_FTYPE_MOSTLY_Q4_1; break; case GGML_TYPE_Q5_0: ftype = LLAMA_FTYPE_MOSTLY_Q5_0; break; case GGML_TYPE_Q5_1: ftype = LLAMA_FTYPE_MOSTLY_Q5_1; break; + case GGML_TYPE_Q6_0: ftype = LLAMA_FTYPE_MOSTLY_Q6_0; break; case GGML_TYPE_Q8_0: ftype = LLAMA_FTYPE_MOSTLY_Q8_0; break; case GGML_TYPE_Q2_K: ftype = LLAMA_FTYPE_MOSTLY_Q2_K; break; case GGML_TYPE_Q3_K: ftype = LLAMA_FTYPE_MOSTLY_Q3_K_M; break; @@ -4471,6 +4472,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) { case LLAMA_FTYPE_MOSTLY_Q4_1: return "Q4_1"; case LLAMA_FTYPE_MOSTLY_Q5_0: return "Q5_0"; case LLAMA_FTYPE_MOSTLY_Q5_1: return "Q5_1"; + case LLAMA_FTYPE_MOSTLY_Q6_0: return "Q6_0"; case LLAMA_FTYPE_MOSTLY_Q8_0: return "Q8_0"; case LLAMA_FTYPE_MOSTLY_Q2_K: return "Q2_K - Medium"; case LLAMA_FTYPE_MOSTLY_Q2_K_S: return "Q2_K - Small"; @@ -15967,6 +15969,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s case LLAMA_FTYPE_MOSTLY_Q4_1: default_type = GGML_TYPE_Q4_1; break; case LLAMA_FTYPE_MOSTLY_Q5_0: default_type = GGML_TYPE_Q5_0; break; case LLAMA_FTYPE_MOSTLY_Q5_1: default_type = GGML_TYPE_Q5_1; break; + case LLAMA_FTYPE_MOSTLY_Q6_0: default_type = GGML_TYPE_Q6_0; break; case LLAMA_FTYPE_MOSTLY_Q8_0: default_type = GGML_TYPE_Q8_0; break; case LLAMA_FTYPE_MOSTLY_F16: default_type = GGML_TYPE_F16; break; case LLAMA_FTYPE_MOSTLY_BF16: default_type = GGML_TYPE_BF16; break; |