ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-09 16:00:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Nexes the Elder
2024-11-21 07:12:57 +01:00
committed by Iwan Kawrakow
parent 4d2fbde0cb
commit 8ad84b9fab
1 changed files with 1 additions and 1 deletions
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");