Skip to content

AdaLora + bnb not working #1113

@BenjaminBossan

Description

@BenjaminBossan

System Info

Who can help?

No response

Information

  • The official example scripts
  • My own modified scripts

Tasks

  • An officially supported task in the examples folder
  • My own task or dataset (give details below)

Reproduction

The issue is this line:

compute_dtype = lora_A.weight.dtype

In AdaLoRA, lora_A and lora_B are not ModuleDicts but ParameterDicts, so lora_A[adapter_name].weight.dtype does not exist, it should just be lora_A[adapter_name].dtype.

Furthermore, using AdaLoRA with 8bit bnb gives NaNs for me for opt-125m.

Expected behavior

AdaLoRA + bnb should work.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions