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

Merge pull request #415 from lexin4ever/patch-1

Browse source 
server: pass seed param from command line to llama
This commit is contained in:
Andrei 2023-06-23 10:09:38 -04:00 committed by GitHub
commit 0952d533fe
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
llama_cpp/server/app.py
View file

@ -30,6 +30,9 @@ class Settings(BaseSettings):
ge=0, ge=0,
description="The number of layers to put on the GPU. The rest will be on the CPU.", description="The number of layers to put on the GPU. The rest will be on the CPU.",
) )
seed: int = Field(
default=1337, description="Random seed. -1 for random."
)
n_batch: int = Field( n_batch: int = Field(
default=512, ge=1, description="The batch size to use per eval." default=512, ge=1, description="The batch size to use per eval."
) )
@ -109,6 +112,7 @@ def create_app(settings: Optional[Settings] = None):
llama = llama_cpp.Llama( llama = llama_cpp.Llama(
model_path=settings.model, model_path=settings.model,
n_gpu_layers=settings.n_gpu_layers, n_gpu_layers=settings.n_gpu_layers,
seed=settings.seed,
f16_kv=settings.f16_kv, f16_kv=settings.f16_kv,
use_mlock=settings.use_mlock, use_mlock=settings.use_mlock,
use_mmap=settings.use_mmap, use_mmap=settings.use_mmap,