diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index f628d0642..d172f645a 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -14,25 +14,25 @@ struct quant_option { }; static const std::vector QUANT_OPTIONS = { - { "Q4_0", LLAMA_FTYPE_MOSTLY_Q4_0, " 3.50G, +0.2499 ppl @ 7B", }, - { "Q4_1", LLAMA_FTYPE_MOSTLY_Q4_1, " 3.90G, +0.1846 ppl @ 7B", }, - { "Q5_0", LLAMA_FTYPE_MOSTLY_Q5_0, " 4.30G, +0.0796 ppl @ 7B", }, - { "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 4.70G, +0.0415 ppl @ 7B", }, + { "Q4_0", LLAMA_FTYPE_MOSTLY_Q4_0, " 3.56G, +0.2166 ppl @ LLaMA-v1-7B", }, + { "Q4_1", LLAMA_FTYPE_MOSTLY_Q4_1, " 3.90G, +0.1585 ppl @ LLaMA-v1-7B", }, + { "Q5_0", LLAMA_FTYPE_MOSTLY_Q5_0, " 4.33G, +0.0683 ppl @ LLaMA-v1-7B", }, + { "Q5_1", LLAMA_FTYPE_MOSTLY_Q5_1, " 4.70G, +0.0349 ppl @ LLaMA-v1-7B", }, #ifdef GGML_USE_K_QUANTS - { "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.67G, +0.8698 ppl @ 7B", }, + { "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.63G, +0.6717 ppl @ LLaMA-v1-7B", }, { "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" }, - { "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 2.75G, +0.5505 ppl @ 7B", }, - { "Q3_K_M", LLAMA_FTYPE_MOSTLY_Q3_K_M, " 3.06G, +0.2437 ppl @ 7B", }, - { "Q3_K_L", LLAMA_FTYPE_MOSTLY_Q3_K_L, " 3.35G, +0.1803 ppl @ 7B", }, + { "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", }, { "Q4_K", LLAMA_FTYPE_MOSTLY_Q4_K_M, "alias for Q4_K_M", }, - { "Q4_K_S", LLAMA_FTYPE_MOSTLY_Q4_K_S, " 3.56G, +0.1149 ppl @ 7B", }, - { "Q4_K_M", LLAMA_FTYPE_MOSTLY_Q4_K_M, " 3.80G, +0.0535 ppl @ 7B", }, + { "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_S", LLAMA_FTYPE_MOSTLY_Q5_K_S, " 4.33G, +0.0353 ppl @ 7B", }, - { "Q5_K_M", LLAMA_FTYPE_MOSTLY_Q5_K_M, " 4.45G, +0.0142 ppl @ 7B", }, - { "Q6_K", LLAMA_FTYPE_MOSTLY_Q6_K, " 5.15G, +0.0044 ppl @ 7B", }, + { "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", }, #endif - { "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ 7B", }, + { "Q8_0", LLAMA_FTYPE_MOSTLY_Q8_0, " 6.70G, +0.0004 ppl @ LLaMA-v1-7B", }, { "F16", LLAMA_FTYPE_MOSTLY_F16, "13.00G @ 7B", }, { "F32", LLAMA_FTYPE_ALL_F32, "26.00G @ 7B", }, };