model-conversion : remove -fa option in model card template [no ci] (#18088)

This commit updates the causal model card template and removes the
-fa option as it is no longer required (fa is auto detected).
This commit is contained in:
Daniel Bevenius
2025-12-16 13:25:09 +01:00
committed by GitHub
parent 7f2b2f3c77
commit 79dbae034a

View 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