[BUG] <title>lora微调minicpmv2.6报错

[jinhuazhong]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

报错信息：

测试数据：

bash文件：
`#!/bin/bash

GPUS_PER_NODE=1
NNODES=1
NODE_RANK=0
MASTER_ADDR=localhost
MASTER_PORT=6001

MODEL="/home/model/OpenBMB/MiniCPM-V-2_6"

or openbmb/MiniCPM-V-2, openbmb/MiniCPM-Llama3-V-2_5, openbmb/MiniCPM-V-2_6

ATTENTION: specify the path to your training data, which should be a json file consisting of a list of conversations.

See the section for finetuning in README for more information.

DATA="/home/data/train/test.json"
EVAL_DATA="/home/data/train/test.json"

if use openbmb/MiniCPM-V-2, please set LLM_TYPE=minicpm, if use openbmb/MiniCPM-Llama3-V-2_5, please set LLM_TYPE="llama3",

if use openbmb/MiniCPM-o-2_6 or openbmb/MiniCPM-V-2_6, please set LLM_TYPE=qwen

LLM_TYPE="minicpm"
MODEL_MAX_Length=2048 # if conduct multi-images sft, please set MODEL_MAX_Length=4096

DISTRIBUTED_ARGS="
--nproc_per_node $GPUS_PER_NODE
--nnodes $NNODES
--node_rank $NODE_RANK
--master_addr $MASTER_ADDR
--master_port $MASTER_PORT
"

torchrun $DISTRIBUTED_ARGS finetune.py
--model_name_or_path $MODEL
--llm_type $LLM_TYPE
--data_path $DATA
--eval_data_path $EVAL_DATA
--remove_unused_columns false
--label_names "labels"
--prediction_loss_only false
--bf16 false
--bf16_full_eval false
--fp16 true
--fp16_full_eval true
--do_train
--do_eval
--tune_vision true
--tune_llm false
--use_lora true
--lora_target_modules "llm..*layers.\d+.self_attn.(q_proj|k_proj|v_proj|o_proj)"
--model_max_length $MODEL_MAX_Length
--max_slice_nums 9
--max_steps 10000
--eval_steps 1000
--output_dir output/output__lora
--logging_dir output/output_lora
--logging_strategy "steps"
--per_device_train_batch_size 1
--per_device_eval_batch_size 1
--gradient_accumulation_steps 1
--save_strategy "steps"
--save_steps 1000
--save_total_limit 10
--learning_rate 1e-6
--weight_decay 0.1
--adam_beta2 0.95
--warmup_ratio 0.01
--lr_scheduler_type "cosine"
--logging_steps 1
--gradient_checkpointing true
--deepspeed ds_config_zero2.json
--report_to "tensorboard" # wandb
`

期望行为 | Expected Behavior

No response

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:
- Python:
- Transformers:
- PyTorch:
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):

备注 | Anything else?

No response

[ZMXJJ]

You can try to change LLM_TYPE="minicpm" to LLM_TYPE="qwen" in your script—MiniCPM-V-2.6 is built on the Qwen architecture, so that’s likely why you’re hitting the image token mismatch error.