ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-07 15:00:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update IQ1_TN and IQ2_TN bpw shown to user

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-09-25 13:27:39 +03:00
parent 7784c8928f
commit 0bade93228
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/quantize/quantize.cpp
View File

@@ -28,8 +28,8 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
{ "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", },
{ "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", },
{ "IQ1_TN", LLAMA_FTYPE_MOSTLY_IQ1_TN, " 1.69 bpw quantization (TriLM)", },
{ "IQ2_TN", LLAMA_FTYPE_MOSTLY_IQ2_TN, " 2.06 bpw quantization (TriLM)", },
{ "IQ1_TN", LLAMA_FTYPE_MOSTLY_IQ1_TN, " 1.63 bpw quantization (TriLM)", },
{ "IQ2_TN", LLAMA_FTYPE_MOSTLY_IQ2_TN, " 2.00 bpw quantization (TriLM)", },
{ "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", },