💡 [REQUEST] - <title>Unrecognized configuration class to build an AutoTokenizer

[Guangming92]

起始日期 | Start Date

No response

实现PR | Implementation PR

No response

相关Issues | Reference Issues

通过案例，对模型进行微调，依据给的demo进行参数合并，合并后的模型在加载推理的时候，报Unrecognized configuration class to build an AutoTokenizer错误

摘要 | Summary

执行合并程序如下：
from peft import AutoPeftModelForCausalLM

model = AutoPeftModelForCausalLM.from_pretrained(
path_to_adapter, # path to the output directory
device_map="auto",
trust_remote_code=True
).eval()

merged_model = model.merge_and_unload()
merged_model.save_pretrained(new_model_directory, max_shard_size="2048MB", safe_serialization=True)

基本示例 | Basic Example

无

缺陷 | Drawbacks

未解决问题 | Unresolved questions

No response