titaniumtown/server-config
Archived
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

llama-cpp: gemma 4 E4B -> gemma 4 E2B
All checks were successful
Build and Deploy / deploy (push) Successful in 2m5s

Browse Source
This commit is contained in:
Simon Gardling
2026-04-06 01:24:25 -04:00
parent 8fddd3a954
commit 06aee5af77
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
services/llama-cpp/llama-cpp.nix
View File

@@ -9,8 +9,8 @@
}:
let
cfg = config.services.llama-cpp;
modelUrl = "https://huggingface.co/unsloth/gemma-4-E4B-it-GGUF/resolve/main/gemma-4-E4B-it-Q4_K_M.gguf";
modelAlias = lib.removeSuffix ".gguf" (builtins.baseNameOf modelUrl);
modelUrl = "https://huggingface.co/bartowski/google_gemma-4-E2B-it-GGUF/resolve/main/google_gemma-4-E2B-it-Q4_K_M.gguf";
modelAlias = lib.removeSuffix ".gguf" (baseNameOf modelUrl);
in
{
services.llama-cpp = {
@@ -18,7 +18,7 @@ in
model = toString (
pkgs.fetchurl {
url = modelUrl;
sha256 = "sha256-4bxEJwn+eAqksuybIsFqf83/VC8X8B7Q4yAxFNKPnzQ=";
sha256 = "5efe645db4e1909c7a1f4a9608df18e6c14383f5e86777fc49f769f9ba7d5fdf";
}
);
port = service_configs.ports.private.llama_cpp.port;