ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into ik/try_trellis

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-01-24 15:49:23 +02:00
parent 3a9926b932 814d3e054c
commit 385a4f596c
23 changed files with 11987 additions and 1041 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
examples/quantize/quantize.cpp
View File

@@ -22,50 +22,74 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
{ "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 4.70G, +0.0349 ppl @ LLaMA-v1-7B", },
{ "Q6_0", LLAMA_FTYPE_MOSTLY_Q6_0, " 6.5 bpw quantization", },
{ "IQ2_XXS", LLAMA_FTYPE_MOSTLY_IQ2_XXS, " 2.06 bpw quantization", },
{ "IQ2_XXS_R4",LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4,"IQ2_XXS repacked", },
{ "IQ2_XS", LLAMA_FTYPE_MOSTLY_IQ2_XS, " 2.31 bpw quantization", },
{ "IQ2_XS_R4",LLAMA_FTYPE_MOSTLY_IQ2_XS_R4,"IQ2_XS repacked", },
{ "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", },
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },
{ "IQ2_M_R4", LLAMA_FTYPE_MOSTLY_IQ2_M_R4, " 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", },
{ "IQ1_BN", LLAMA_FTYPE_MOSTLY_IQ1_BN, " 1.62 bpw quantization (Bitnet)", },
{ "IQ2_BN", LLAMA_FTYPE_MOSTLY_IQ2_BN, " 2.00 bpw quantization (Bitnet)", },
{ "IQ2_BN_R4",LLAMA_FTYPE_MOSTLY_IQ2_BN_R4," 2.00 bpw quantization (Bitnet)", },
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", },
{ "Q2_K_R4", LLAMA_FTYPE_MOSTLY_Q2_K_R4, "Q2_K_S repacked", },
{ "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", },
{ "IQ3_KT", LLAMA_FTYPE_MOSTLY_IQ3_KT, " 3.125 bpw trellis quantization", },
{ "IQ4_KT", LLAMA_FTYPE_MOSTLY_IQ4_KT, " 4.0 bpw trellis quantization", },
{ "IQ3_XXS_R4",LLAMA_FTYPE_MOSTLY_IQ3_XXS_R4,"IQ3_XXS repacked", },
{ "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },
{ "IQ3_S_R4", LLAMA_FTYPE_MOSTLY_IQ3_S_R4, "IQ3_S repacked", },
{ "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", },
{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },
{ "Q3_K_R4", LLAMA_FTYPE_MOSTLY_Q3_K_R4, "Q3_K_S repacked" },
{ "IQ3_XS", LLAMA_FTYPE_MOSTLY_IQ3_XS, " 3.3 bpw quantization" , },
{ "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 2.75G, +0.5551 ppl @ LLaMA-v1-7B", },
{ "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.07G, +0.2496 ppl @ LLaMA-v1-7B", },
{ "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", },
{ "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", },
{ "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", },
{ "IQ4_KSS", LLAMA_FTYPE_MOSTLY_IQ4_KSS, " 4.0 bpw non-linear quantization", },
{ "IQ2_K", LLAMA_FTYPE_MOSTLY_IQ2_K, " 2.375 bpw non-linear quantization",},
{ "IQ2_K_R4", LLAMA_FTYPE_MOSTLY_IQ2_K_R4, "IQ2_K repacked",},
{ "IQ2_KS", LLAMA_FTYPE_MOSTLY_IQ2_KS, " 2.1875 bpw non-linear quantization",},
{ "IQ2_KT", LLAMA_FTYPE_MOSTLY_IQ2_KT, " 2.125 bpw trellis quantization", },
{ "IQ3_K", LLAMA_FTYPE_MOSTLY_IQ3_K, " 3.44 bpw non-linear quantization", },
{ "IQ3_K_R4", LLAMA_FTYPE_MOSTLY_IQ3_K_R4, "IQ3_K repacked", },
{ "IQ3_KL", LLAMA_FTYPE_MOSTLY_IQ3_KL, " 4 bpw non-linear quantization mix",},
{ "IQ4_K", LLAMA_FTYPE_MOSTLY_IQ4_K, " 4.5 bpw non-linear quantization", },
{ "IQ4_K_R4", LLAMA_FTYPE_MOSTLY_IQ4_K_R4, "IQ4_K repacked", },
{ "IQ5_K", LLAMA_FTYPE_MOSTLY_IQ5_K, " 5.5 bpw non-linear quantization", },
{ "IQ5_K_R4", LLAMA_FTYPE_MOSTLY_IQ5_K_R4, "IQ5_K repacked", },
{ "IQ6_K", LLAMA_FTYPE_MOSTLY_IQ6_K, " 6.6 bpw non-linear quantization", },
{ "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", },
{ "Q4_K_R4", LLAMA_FTYPE_MOSTLY_Q4_K_R4, "Q4_K_S repacked", },
{ "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.59G, +0.0992 ppl @ LLaMA-v1-7B", },
{ "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 3.80G, +0.0532 ppl @ LLaMA-v1-7B", },
{ "Q5_K", LLAMA_FTYPE_MOSTLY_Q5_K_M, "alias for Q5_K_M", },
{ "Q5_K_R4", LLAMA_FTYPE_MOSTLY_Q5_K_R4, "Q5_K_S repacked", },
{ "Q5_K_S", LLAMA_FTYPE_MOSTLY_Q5_K_S, " 4.33G, +0.0400 ppl @ LLaMA-v1-7B", },
{ "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 4.45G, +0.0122 ppl @ LLaMA-v1-7B", },
{ "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 5.15G, +0.0008 ppl @ LLaMA-v1-7B", },
{ "Q6_K_R4", LLAMA_FTYPE_MOSTLY_Q6_K_R4, "Q6_K repacked", },
{ "Q8_K_R8", LLAMA_FTYPE_MOSTLY_Q8_K_R8, "Q8_K repacked", },
{ "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", },
{ "Q4_0_4_4", LLAMA_FTYPE_MOSTLY_Q4_0_4_4, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
{ "Q4_0_4_8", LLAMA_FTYPE_MOSTLY_Q4_0_4_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
{ "Q4_0_8_8", LLAMA_FTYPE_MOSTLY_Q4_0_8_8, " 4.34G, +0.4685 ppl @ Llama-3-8B", },
{ "F16", LLAMA_FTYPE_MOSTLY_F16, "14.00G, -0.0020 ppl @ Mistral-7B", },
{ "BF16", LLAMA_FTYPE_MOSTLY_BF16, "14.00G, -0.0050 ppl @ Mistral-7B", },
{ "BF16_R16", LLAMA_FTYPE_MOSTLY_BF16_R16, "14.00G, -0.0050 ppl @ Mistral-7B", },
{ "F32", LLAMA_FTYPE_ALL_F32, "26.00G @ 7B", },
// Note: Ensure COPY comes after F32 to avoid ftype 0 from matching.
{ "COPY", LLAMA_FTYPE_ALL_F32, "only copy tensors, no quantizing", },
@@ -486,8 +510,8 @@ int main(int argc, char ** argv) {
if (!params.ignore_imatrix_rules && imatrix_data.empty() &&
(params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS_R4 ||
params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS_R4 ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M)) {
fprintf(stderr, "\n==========================================================================================================\n");