diff options
Diffstat (limited to 'examples/quantize')
| -rw-r--r-- | examples/quantize/quantize.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/examples/quantize/quantize.cpp b/examples/quantize/quantize.cpp index 7bdd8597..7ceee208 100644 --- a/examples/quantize/quantize.cpp +++ b/examples/quantize/quantize.cpp @@ -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", }, |