examples/inference/llama3_lora_sft.yaml

model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
adapter_name_or_path: saves/llama3-8b/lora/sft
template: llama3
infer_backend: huggingface  # choices: [huggingface, vllm, sglang]
trust_remote_code: true