vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)

Browse source
This commit is contained in:
Rand Xie 2023-07-28 01:42:53 -07:00 • committed by GitHub
parent edcc7ae7d2
commit 65cdf34bdc
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/save-load-state/save-load-state.cpp
View file

@ -26,6 +26,7 @@ int main(int argc, char ** argv) {
auto lparams = llama_context_default_params();
lparams.n_ctx = params.n_ctx;
lparams.n_gqa = params.n_gqa;
lparams.seed = params.seed;
lparams.f16_kv = params.memory_f16;
lparams.use_mmap = params.use_mmap;