开发者社区 > ModelScope模型即服务 > 正文

ModelScope中,这个警告是什么原因,可以去掉吗?

"跑ModelScope这个模型是可以的model_type = ModelType.llama3_llava_next_8b
。但这个模型与llava1_6_mistral_7b_instruct输出是对的,但会报满屏幕的警告。 warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/wzdata1/anaconda3/envs/swift/lib/python3.9/site-packages/torch/nn/modules/module.py:2047: UserWarning: for vision_model.encoder.layers.23.mlp.fc1.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass assign=True to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/wzdata1/anaconda3/envs/swift/lib/python3.9/site-packages/torch/nn/modules/module.py:2047: UserWarning: for vision_model.encoder.layers.23.mlp.fc1.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass assign=True to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/wzdata1/anaconda3/envs/swift/lib/python3.9/site-packages/torch/nn/modules/module.py:2047: UserWarning: for vision_model.encoder.layers.23.mlp.fc2.weight: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass assign=True to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?)
warnings.warn(f'for {key}: copying from a non-meta parameter in the checkpoint to a meta '
/wzdata1/anaconda3/envs/swift/lib/python3.9/site-packages/torch/nn/modules/module.py:2047: UserWarning: for vision_model.encoder.layers.23.mlp.fc2.bias: copying from a non-meta parameter in the checkpoint to a meta parameter in the current model, which is a no-op. (Did you mean to pass assign=True to assign items in the state dictionary to their corresponding key in the module instead of copying them in place?) ModelScope中,这个警告是什么原因,可以去掉吗?"

展开
收起
小小爱吃香菜 2024-07-09 20:41:45 160 0
1 条回答
写回答
取消 提交回答
  • "torch您用2.3.0看看,llava1_6-vicuna-13b-instruct测了没问题。 cd swift
    pip install -e .
    源码安装您再试一下看看。此回答整理自钉群“魔搭ModelScope开发者联盟群 ①”"

    2024-07-09 22:09:10
    赞同 3 展开评论 打赏

ModelScope旨在打造下一代开源的模型即服务共享平台,为泛AI开发者提供灵活、易用、低成本的一站式模型服务产品,让模型应用更简单!欢迎加入技术交流群:微信公众号:魔搭ModelScope社区,钉钉群号:44837352

热门讨论

热门文章

相关电子书

更多
视觉AI能力的开放现状及ModelScope实战 立即下载
ModelScope助力语音AI模型创新与应用 立即下载
低代码开发师(初级)实战教程 立即下载