Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 06:39:25 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add llama enum for IQ2_XS

Browse Source
This commit is contained in:
Iwan Kawrakow 2024-01-11 18:24:12 +02:00
parent a1610b05b2
commit 9bfcb16fd3
2 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llama.cpp
View File

@ -2223,6 +2223,7 @@ struct llama_model_loader {
case GGML_TYPE_Q5_K: ftype = LLAMA_FTYPE_MOSTLY_Q5_K_M; break;
case GGML_TYPE_Q6_K: ftype = LLAMA_FTYPE_MOSTLY_Q6_K; break;
case GGML_TYPE_IQ2_XXS: ftype = LLAMA_FTYPE_MOSTLY_IQ2_XXS; break;
case GGML_TYPE_IQ2_XS: ftype = LLAMA_FTYPE_MOSTLY_IQ2_XS; break;
default:
{
LLAMA_LOG_WARN("%s: unknown type %s\n", __func__, ggml_type_name(type_max));
@ -2595,6 +2596,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) {
case LLAMA_FTYPE_MOSTLY_Q5_K_M: return "Q5_K - Medium";
case LLAMA_FTYPE_MOSTLY_Q6_K: return "Q6_K";
case LLAMA_FTYPE_MOSTLY_IQ2_XXS:return "IQ2_XSS - 2.0625 bpw";
case LLAMA_FTYPE_MOSTLY_IQ2_XS: return "IQ2_XS - 2.3125 bpw";
default: return "unknown, may not work";
}
@ -9041,6 +9043,7 @@ static void llama_model_quantize_internal(const std::string & fname_inp, const s
case LLAMA_FTYPE_MOSTLY_Q5_K_M: quantized_type = GGML_TYPE_Q5_K; break;
case LLAMA_FTYPE_MOSTLY_Q6_K: quantized_type = GGML_TYPE_Q6_K; break;
case LLAMA_FTYPE_MOSTLY_IQ2_XXS:quantized_type = GGML_TYPE_IQ2_XXS; break;
case LLAMA_FTYPE_MOSTLY_IQ2_XS :quantized_type = GGML_TYPE_IQ2_XS; break;
default: throw std::runtime_error(format("invalid output file type %d\n", ftype));
}

1
llama.h
View File

@ -104,6 +104,7 @@ extern "C" {
LLAMA_FTYPE_MOSTLY_Q5_K_M = 17, // except 1d tensors
LLAMA_FTYPE_MOSTLY_Q6_K = 18, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_XXS = 19, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_XS = 20, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};