CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add TQ1_0 and TQ2_0 ternary quantization types

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-07-30 17:55:54 -04:00
parent 79a278e922
commit 77b8f84ae7
10 changed files with 563 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/quantize/quantize.cpp
View File

@@ -26,6 +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", },
{ "TQ1_0", LLAMA_FTYPE_MOSTLY_TQ1_0, " 1.69 bpw ternarization", },
{ "TQ2_0", LLAMA_FTYPE_MOSTLY_TQ2_0, " 2.06 bpw ternarization", },
{ "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", },