tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

bitnet : replace 1.58b with b1.58, as in the paper

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-06-28 20:38:12 -04:00
parent 0996149911
commit bfd2f21fb4
5 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/quantize/quantize.cpp
View File

@ -26,8 +26,8 @@ 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", },
{ "Q1_3", LLAMA_FTYPE_MOSTLY_Q1_3, " 1.63 bpw for BitNet 1.58b", },
{ "Q2_2", LLAMA_FTYPE_MOSTLY_Q2_2, " 2.00 bpw for BitNet 1.58b", },
{ "Q1_3", LLAMA_FTYPE_MOSTLY_Q1_3, " 1.63 bpw for BitNet b1.58", },
{ "Q2_2", LLAMA_FTYPE_MOSTLY_Q2_2, " 2.00 bpw for BitNet b1.58", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.96G, +3.5199 ppl @ Llama-3-8B", },
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.96G, +3.1836 ppl @ Llama-3-8B", },
{ "IQ3_XXS",LLAMA_FTYPE_MOSTLY_IQ3_XXS," 3.06 bpw quantization", },