ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-21 23:19:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Adding iq1_tn - 1.6875 bpw for TriLM ternary models

Browse Source
This commit is contained in:
Iwan Kawrakow
2024-09-08 17:56:15 +03:00
parent bf4b19b474
commit c82bf200ce
10 changed files with 157 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
include/llama.h
View File

@@ -166,14 +166,16 @@ 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_IQ1_BN = 36, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_BN = 37, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_K = 38, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ3_K = 39, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_K = 40, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_K = 41, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ6_K = 42, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_TN = 43, // except 1d tensors
//
LLAMA_FTYPE_MOSTLY_IQ1_BN = 136, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_BN = 137, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_K = 138, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ3_K = 139, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ4_K = 140, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ5_K = 141, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ6_K = 142, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ2_TN = 143, // except 1d tensors
LLAMA_FTYPE_MOSTLY_IQ1_TN = 144, // except 1d tensors
LLAMA_FTYPE_GUESSED = 1024, // not specified in the model file
};