huggingface config_error ai_generated true

ValueError: 目标模块 ['q_proj', 'v_proj'] 在基础模型中未找到。可用模块为: ['query', 'value', 'key', 'output']

ValueError: Target modules ['q_proj', 'v_proj'] not found in the base model. Available modules are: ['query', 'value', 'key', 'output']

ID: huggingface/peft-lora-target-modules-mismatch

其他格式: JSON · Markdown 中文 · English
85%修复率
88%置信度
1证据数
2023-06-15首次发现

版本兼容性

版本状态引入弃用备注
peft>=0.4.0 active — — —
transformers>=4.30.0 active — — —
torch>=1.13.0 active — — —

根因分析

LoRA 的 target_modules 参数指定了错误的模块名称，与基础模型实际的层命名约定不匹配。

English

LoRA target_modules specified with incorrect module names that do not match the base model's actual layer naming convention.

generic

官方文档

https://huggingface.co/docs/peft/en/developer_guides/lora#target-modules

解决方案

  1. Print the model's module names to identify correct target modules: `for name, _ in model.named_modules(): print(name)` then select only linear layers (e.g., 'q_proj', 'v_proj' for LLaMA, 'query', 'value' for BERT).
  2. Use peft.get_peft_model() with target_modules='all-linear' if using peft>=0.7.0 and the model is transformer-based, which automatically selects all linear layers except the output projection.
  3. Check the model configuration via model.config.model_type and refer to the PEFT documentation for the correct module names for that architecture.

无效尝试

常见但无效的做法:

  1. 50% 失败

    The model may not have those exact names; e.g., LLaMA uses 'self_attn.q_proj' while GPT-2 uses 'attn.c_attn'. This can still fail if names are wrong.

  2. 30% 失败

    Includes non-linear layers (e.g., activation functions) which are invalid for LoRA and cause shape errors during forward pass.

  3. 40% 失败

    'all-linear' was introduced in peft>=0.7.0; older versions raise AttributeError or silently ignore it.