快速入门

导出

您可以轻松地将 🤗 Transformers 模型导出到 ExecuTorch

optimum-cli export executorch --model meta-llama/Llama-3.2-1B --recipe xnnpack --output_dir meta_llama3_2_1b_executorch

推理

要加载模型并运行推理，您只需将 `AutoModelForCausalLM` 类替换为相应的 `ExecuTorchModelForCausalLM` 类。您还可以在加载模型时即时加载 PyTorch 检查点并将其转换为 ExecuTorch。

- from transformers import AutoModelForCausalLM
+ from optimum.executorch import ExecuTorchModelForCausalLM
  from transformers import AutoTokenizer

  model_id = "meta-llama/Llama-3.2-1B"
  tokenizer = AutoTokenizer.from_pretrained(model_id)
- model = AutoModelForCausalLM.from_pretrained(model_id)
+ model = ExecuTorchModelForCausalLM.from_pretrained(model_id)