enginex-mthreads-llama.cpp/examples/model-conversion/scripts/causal/modelcard.template

---
base_model:
- {base_model}
---
# {model_name} GGUF

Recommended way to run this model:

```sh
llama-server -hf {namespace}/{model_name}-GGUF -c 0
```

Then, access http://localhost:8080
Sync from upstream `llama.cpp` repository 2026-01-16 10:43:34 +08:00			`---`
			`base_model:`
			`- {base_model}`
			`---`
			`# {model_name} GGUF`

			`Recommended way to run this model:`

			```sh
sync from b7516 2026-01-16 11:16:14 +08:00			`llama-server -hf {namespace}/{model_name}-GGUF -c 0`
Sync from upstream `llama.cpp` repository 2026-01-16 10:43:34 +08:00			```

			`Then, access http://localhost:8080`