sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-14 13:04:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

clean code

Browse Source
This commit is contained in:
root
2024-06-09 20:22:03 +08:00
parent dbee0a86c1
commit 1c5a8b7fec
7 changed files with 64 additions and 216 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View File

@@ -26,7 +26,7 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },
{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
{ "I2_S", LLAMA_FTYPE_MOSTLY_I2, " 2 bpw per-tensor", },
{ "I2_S", LLAMA_FTYPE_MOSTLY_I2_S, " 2 bpw per-tensor quantization", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", },
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.16G, +9.0634 ppl @ LLaMA-v1-7B", },
{ "IQ3_XXS",LLAMA_FTYPE_MOSTLY_IQ3_XXS," 3.06 bpw quantization", },