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

make rms_norm_eps a parameter (#2374)

Browse source 
* make rms_norm_eps a parameter

* add rms_norm_eps to command line

* fix baby llama, test-grad0

* use scientific notation for eps param in the help

ggml-ci
This commit is contained in:
slaren 2023-07-24 17:57:12 +02:00 • committed by GitHub
parent b3f138d058
commit 41c674161f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
11 changed files with 89 additions and 56 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama.h
View file

@ -87,6 +87,7 @@ extern "C" {
int32_t n_ctx; // text context
int32_t n_batch; // prompt processing batch size
int32_t n_gqa; // grouped-query attention (TEMP - will be moved to model hparams)
float rms_norm_eps; // rms norm epsilon (TEMP - will be moved to model hparams)
int32_t n_gpu_layers; // number of layers to store in VRAM
int32_t main_gpu; // the GPU that is used for scratch and small tensors