sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-14 13:04:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix URL for draft model

Browse Source
This commit is contained in:
Georgi Gerganov
2026-05-08 08:03:49 +03:00
parent 6a4b05a030
commit 12c7cfbe83
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tools/server/tests/unit/test_speculative.py
View File

@@ -5,7 +5,7 @@ from utils import *
server = ServerPreset.stories15m_moe()
MODEL_DRAFT_FILE_URL = "https://huggingface.co/ggml-org/models/resolve/main/tinyllamas/stories15M-q4_0.gguf"
MODEL_DRAFT_FILE_URL = "https://huggingface.co/ggml-org/tiny-llamas/resolve/main/stories15M-q4_0.gguf"
def create_server():
global server