ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-27 01:29:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Rename q4_0_r4, q8_0_r4 and iq4_xs_r4 to _r8 (#189)

Browse Source 
* Rename q4_0_r4 to q4_0_r8 to reflect actual row interleaving

* Rename q8_0_r4 to q8_0_r8 to reflect actual row interleaving

* Rename iq4_xs_r4 to iq4_xs_r8 to reflect actual row interleaving

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2025-02-06 18:45:28 +02:00
committed by GitHub
parent 7c94c3da56
commit 8049ffcbc8
10 changed files with 196 additions and 196 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/quantize/quantize.cpp
View File

@@ -51,11 +51,11 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1764 ppl @ LLaMA-v1-7B", },
{ "IQ4_NL", LLAMA_FTYPE_MOSTLY_IQ4_NL, " 4.50 bpw non-linear quantization", },
{ "IQ4_NL_R4",LLAMA_FTYPE_MOSTLY_IQ4_NL_R4," 4.50 bpw non-linear quantization", },
{ "IQ4_XS_R4",LLAMA_FTYPE_MOSTLY_IQ4_XS_R4," 4.25 bpw non-linear quantization", },
{ "Q4_0_R4", LLAMA_FTYPE_MOSTLY_Q4_0_R4, " 4.50 bpw quantization", },
{ "IQ4_XS_R8",LLAMA_FTYPE_MOSTLY_IQ4_XS_R8," 4.25 bpw non-linear quantization", },
{ "Q4_0_R8", LLAMA_FTYPE_MOSTLY_Q4_0_R8, " 4.50 bpw quantization", },
{ "Q5_0_R4", LLAMA_FTYPE_MOSTLY_Q5_0_R4, " 5.50 bpw quantization", },
{ "Q6_0_R4", LLAMA_FTYPE_MOSTLY_Q6_0_R4, " 6.50 bpw quantization", },
{ "Q8_0_R4", LLAMA_FTYPE_MOSTLY_Q8_0_R4, " 8.50 bpw quantization", },
{ "Q8_0_R8", LLAMA_FTYPE_MOSTLY_Q8_0_R8, " 8.50 bpw quantization", },
{ "IQ4_XS", LLAMA_FTYPE_MOSTLY_IQ4_XS, " 4.25 bpw non-linear quantization", },
{ "IQ4_KS", LLAMA_FTYPE_MOSTLY_IQ4_KS, " 4.25 bpw non-linear quantization", },
{ "IQ4_KS_R4",LLAMA_FTYPE_MOSTLY_IQ4_KS_R4,"IQ4_KS repacked", },