tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 20:58:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix MiniCPM (#5392)

Browse Source 
* fix bug for norm_rms_eps missing

* to align with the same order as convert.py for model write

* fix: undo HF models permute tensor

* update for flake8 lint
This commit is contained in:
runfuture
2024-02-08 18:36:19 +08:00
committed by GitHub
parent a6e514a85f
commit 4aa43fab56
2 changed files with 63 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
llama.cpp
View File

@ -2947,6 +2947,8 @@ static void llm_load_hparams(
} break;
case LLM_ARCH_MINICPM:
{
ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
switch (hparams.n_layer) {
case 40: model.type = e_model::MODEL_2B; break;
default: model.type = e_model::MODEL_UNKNOWN;