Skip to content

请问现在支持Lora嘛?复现训练使用的全参吧 #4

Closed

Description

@wander996
No description provided.

Activity

  1. dhcode-cpp commented on Feb 13, 2025

    @dhcode-cpp
    Owner

    现在是全参,lora类训练待开发

  2. dhcode-cpp commented on Feb 16, 2025

    @dhcode-cpp
    Owner

    已支持单卡LoRA

    pip install -r requirements.txt
    

    执行

    ACCELERATE_LOG_LEVEL=info \
    accelerate launch \
    --config_file recipes/zero1.yaml \
    --num_processes=1 \
    src/x_r1/grpo.py \
    --config recipes/X_R1_zero_0dot5B_peft_config.yaml \
    > ./output/x_r1_test_sampling.log 2>&1
    
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions