]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commitdiff
model-conversion : remove -fa option in model card template [no ci] (#18088)
authorDaniel Bevenius <redacted>
Tue, 16 Dec 2025 12:25:09 +0000 (13:25 +0100)
committerGitHub <redacted>
Tue, 16 Dec 2025 12:25:09 +0000 (13:25 +0100)
This commit updates the causal model card template and removes the
-fa option as it is no longer required (fa is auto detected).

examples/model-conversion/scripts/causal/modelcard.template

index 87800a1b93a2f00a5abfa62626242bac1c4a22fe..cfa8e6b4334103ea58c428059c4c0cde2d8ac042 100644 (file)
@@ -7,7 +7,7 @@ base_model:
 Recommended way to run this model:
 
 ```sh
-llama-server -hf {namespace}/{model_name}-GGUF -c 0 -fa
+llama-server -hf {namespace}/{model_name}-GGUF -c 0
 ```
 
 Then, access http://localhost:8080