search

QwenLM / Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Apache License 2.0
12.47k stars 1.01k forks source link

💡 [REQUEST] - <title> 关于lora 模型合并的几个问题 #1226

Closed wangyao123456a closed 1 month ago

wangyao123456a commented 2 months ago

起始日期 | Start Date

1

实现PR | Implementation PR

1

相关Issues | Reference Issues

1、请问base model 和lora model 合并完后，新模型的大小、参数量和base model 一样的吗？ 2、推理时如果lora 和base 模型不合并，输出结果和模型合并后推理结果是否一致，有精度上的损失吗？

摘要 | Summary

1

基本示例 | Basic Example

1

缺陷 | Drawbacks

1

未解决问题 | Unresolved questions

1

wangyao123456a commented 2 months ago

1、请问base model 和lora model 合并完后，新模型的大小、参数量和base model 一样的吗？ 2、推理时如果lora 和base 模型不合并，输出结果和模型合并后推理结果是否一致，有精度上的损失吗？

jklj077 commented 2 months ago
  1. It should be the same.
  2. The difference should be negligible.
github-actions[bot] commented 1 month ago

This issue has been automatically marked as inactive due to lack of recent activity. Should you believe it remains unresolved and warrants attention, kindly leave a comment on this thread. 此问题由于长期未有新进展而被系统自动标记为不活跃。如果您认为它仍有待解决，请在此帖下方留言以补充信息。