tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-30 12:55:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : increase context size for the tests

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-02-10 15:00:02 +02:00
parent f9971ef2e1
commit 879ba82777
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/server/tests/utils.py
View File

@ -280,7 +280,7 @@ class ServerPreset:
server.model_hf_repo = "ggml-org/models"
server.model_hf_file = "tinyllamas/stories260K.gguf"
server.model_alias = "tinyllama-2"
server.n_ctx = 256
server.n_ctx = 512
server.n_batch = 32
server.n_slots = 2
server.n_predict = 64