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

llama-cpp: use gpt-oss-20b-mxfp4

Browse Source
This commit is contained in:
Simon Gardling 2025-08-05 19:53:20 -07:00
parent d1bf20f03f
commit ffc079fb21
Signed by: titaniumtown
GPG Key ID: 9AB28AC10ECE533D
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
services/llama-cpp.nix
View File

@ -11,8 +11,8 @@
enable = true;
model = builtins.toString (
pkgs.fetchurl {
url = "https://huggingface.co/bartowski/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/resolve/main/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf";
sha256 = "a71a983c64eb72a2b4a885993cd0675474afe7e92d72b051ab8716b23157daa0";
url = "https://huggingface.co/ggml-org/gpt-oss-20b-GGUF/resolve/main/gpt-oss-20b-mxfp4.gguf";
sha256 = "52f57ab7d3df3ba9173827c1c6832e73375553a846f3e32b49f1ae2daad688d4";
}
);
port = service_configs.ports.llama_cpp;