2 forgotten files
This commit is contained in:
parent
f0806ac943
commit
8bc7a9849e
2 changed files with 6 additions and 0 deletions
|
@ -24,13 +24,16 @@ static const std::vector<struct quant_option> QUANT_OPTIONS = {
|
|||
{ "IQ2_XS", LLAMA_FTYPE_MOSTLY_IQ2_XS, " 2.31 bpw quantization", },
|
||||
{ "IQ2_S", LLAMA_FTYPE_MOSTLY_IQ2_S, " 2.5 bpw quantization", },
|
||||
{ "IQ2_M", LLAMA_FTYPE_MOSTLY_IQ2_M, " 2.7 bpw quantization", },
|
||||
{ "IQ2_XL", LLAMA_FTYPE_MOSTLY_IQ2_XL, " 2.85 bpw quantization mix", },
|
||||
{ "IQ1_S", LLAMA_FTYPE_MOSTLY_IQ1_S, " 1.56 bpw quantization", },
|
||||
{ "IQ1_M", LLAMA_FTYPE_MOSTLY_IQ1_M, " 1.75 bpw quantization", },
|
||||
{ "Q2_K", LLAMA_FTYPE_MOSTLY_Q2_K, " 2.96G, +3.5199 ppl @ Llama-3-8B", },
|
||||
{ "Q2_K_S", LLAMA_FTYPE_MOSTLY_Q2_K_S, " 2.96G, +3.1836 ppl @ Llama-3-8B", },
|
||||
{ "Q2_K_L", LLAMA_FTYPE_MOSTLY_Q2_K_L, " 2.96G, +3.1836 ppl @ Llama-3-8B", },
|
||||
{ "IQ3_XXS", LLAMA_FTYPE_MOSTLY_IQ3_XXS, " 3.06 bpw quantization", },
|
||||
{ "IQ3_S", LLAMA_FTYPE_MOSTLY_IQ3_S, " 3.44 bpw quantization", },
|
||||
{ "IQ3_M", LLAMA_FTYPE_MOSTLY_IQ3_M, " 3.66 bpw quantization mix", },
|
||||
{ "IQ3_XL", LLAMA_FTYPE_MOSTLY_IQ3_XL, " 3.85 bpw quantization mix", },
|
||||
{ "Q3_K", LLAMA_FTYPE_MOSTLY_Q3_K_M, "alias for Q3_K_M" },
|
||||
{ "IQ3_XS", LLAMA_FTYPE_MOSTLY_IQ3_XS, " 3.3 bpw quantization", },
|
||||
{ "Q3_K_S", LLAMA_FTYPE_MOSTLY_Q3_K_S, " 3.41G, +1.6321 ppl @ Llama-3-8B", },
|
||||
|
|
|
@ -166,6 +166,9 @@ extern "C" {
|
|||
LLAMA_FTYPE_MOSTLY_Q4_0_4_4 = 33, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q4_0_4_8 = 34, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q4_0_8_8 = 35, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_IQ2_XL = 36, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_IQ3_XL = 37, // except 1d tensors
|
||||
LLAMA_FTYPE_MOSTLY_Q2_K_L = 38, // except 1d tensors
|
||||
|
||||
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
|
||||
};
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue