diff options
author | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-24 16:42:30 +0200 |
---|---|---|
committer | Iwan Kawrakow <iwan.kawrakow@gmail.com> | 2024-06-24 16:42:30 +0200 |
commit | 707d08792701de5a517c45c6c16bf4d816c00d88 (patch) | |
tree | 1720ae21c0ec450707f7b74b8a67cc4a54aaba31 /llama.cpp | |
parent | 49822f84a9ad633919c40915cde5cb78694c5390 (diff) |
Bitnet: tiny bity faster 1.625 bpw variant on Metal
We get 70.7 t/s for TG-128 vs 69.5 t/s before.
Diffstat (limited to 'llama.cpp')
-rw-r--r-- | llama.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -4130,7 +4130,7 @@ static std::string llama_model_ftype_name(llama_ftype ftype) { case LLAMA_FTYPE_MOSTLY_IQ3_XXS:return "IQ3_XXS - 3.0625 bpw"; case LLAMA_FTYPE_MOSTLY_IQ1_S :return "IQ1_S - 1.5625 bpw"; case LLAMA_FTYPE_MOSTLY_IQ1_M :return "IQ1_M - 1.75 bpw"; - case LLAMA_FTYPE_MOSTLY_IQ1_BN :return "IQ1_BN - 1.75 bpw Bitnet"; + case LLAMA_FTYPE_MOSTLY_IQ1_BN :return "IQ1_BN - 1.625 bpw Bitnet"; case LLAMA_FTYPE_MOSTLY_IQ2_BN :return "IQ2_BN - 2.00 bpw Bitnet"; case LLAMA_FTYPE_MOSTLY_IQ4_NL: return "IQ4_NL - 4.5 bpw"; case LLAMA_FTYPE_MOSTLY_IQ4_XS: return "IQ4_XS - 4.25 bpw"; |