nicolas
/
ik_llama_opt
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Use Q6_0 instead of Q5_1 for tensors incompatible with IQ5_K/Q5_K (#116)

This commit is contained in:
Nexes the Elder 2024-11-21 07:12:57 +01:00 committed by Kawrakow
parent f0a0503ec0
commit 6c73f704ca
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@ -16048,7 +16048,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
case GGML_TYPE_IQ4_K:
case GGML_TYPE_Q4_K: new_type = GGML_TYPE_Q5_0; break;
case GGML_TYPE_IQ5_K:
case GGML_TYPE_Q5_K: new_type = GGML_TYPE_Q5_1; break;
case GGML_TYPE_Q5_K: new_type = GGML_TYPE_Q6_0; break;
case GGML_TYPE_IQ6_K:
case GGML_TYPE_Q6_K: new_type = GGML_TYPE_Q8_0; break;
default: throw std::runtime_error("\nUnsupported tensor size encountered\n");