]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commitdiff
model-conversion : remove -c 0 from model card template [no ci] (#18807)
authorDaniel Bevenius <redacted>
Tue, 13 Jan 2026 13:13:10 +0000 (14:13 +0100)
committerGitHub <redacted>
Tue, 13 Jan 2026 13:13:10 +0000 (14:13 +0100)
This commit removes the `-c, --ctx-size N` from the llama-server
command in the model card template for causal models.

The motivation for this is that -c 0 is the default and specifying it
is redundant.

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

index cfa8e6b4334103ea58c428059c4c0cde2d8ac042..a04595032431c153299527d6d9faae534e84c1e0 100644 (file)
@@ -7,7 +7,7 @@ base_model:
 Recommended way to run this model:
 
 ```sh
-llama-server -hf {namespace}/{model_name}-GGUF -c 0
+llama-server -hf {namespace}/{model_name}-GGUF
 ```
 
 Then, access http://localhost:8080