root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

llama : change fallback type IQ4_NL -> Q4_0

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-07-15 10:27:07 +03:00
parent 0efec57787
commit f6ea7a093c
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
src/llama.cpp
View File

@ -18090,10 +18090,10 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
case GGML_TYPE_IQ1_M:
case GGML_TYPE_Q2_K:
case GGML_TYPE_Q3_K:
case GGML_TYPE_IQ4_XS: new_type = GGML_TYPE_IQ4_NL; break;
case GGML_TYPE_Q4_K: new_type = GGML_TYPE_Q5_0; break;
case GGML_TYPE_Q5_K: new_type = GGML_TYPE_Q5_1; break;
case GGML_TYPE_Q6_K: new_type = GGML_TYPE_Q8_0; break;
case GGML_TYPE_IQ4_XS: new_type = GGML_TYPE_Q4_0; break;
case GGML_TYPE_Q4_K: new_type = GGML_TYPE_Q5_0; break;
case GGML_TYPE_Q5_K: new_type = GGML_TYPE_Q5_1; break;
case GGML_TYPE_Q6_K: new_type = GGML_TYPE_Q8_0; break;
default: throw std::runtime_error("\nUnsupported tensor size encountered\n");
}
LLAMA_LOG_WARN(" - using fallback quantization %s\n", ggml_type_name(new_type));