Lai Wei
Lai Wei
> Hello, I would like to ask how to setup a validation dataset into the finetune stage. In the [MiniGPT-4](https://github.com/Vision-CAIR/MiniGPT-4)/[train_configs](https://github.com/Vision-CAIR/MiniGPT-4/tree/main/train_configs)/minigpt4_stage2_finetune.yaml what should I change so I can have a validation...
您好，请问这个报错您解决了吗
@Jintao-Huang 您好！请问预训练的时候会把数据拼成max length长度吗？还是一条一条的训呢？
@haotian-liu same question. Can you help us on it?
Same questions @junchen14
> 参考LLAVA的方式构建自己的数据集，数据量14w，按照官方给的方式进行finetune，发现进入trainer.train()之后就hang住了，strout和strerr也没有信息，没有报错，请问是哪里不对吗 > > strout中的输出 > > ```python > [2023-12-04 15:00:43,681] [WARNING] [partition_parameters.py:823:_post_init_method] param `cls_token` in MplugOwlVisionEmbeddings not on GPU so was not broadcasted from rank 0 > [2023-12-04 15:00:43,747]...
> yes, the code supports multi-image finetuning Thank you. How should I organize my data for multi-image sft? And how to inference with multi-image?
@qyc-98 Hello! Can you provide some simple examples of in-context inference or SFT? Thanks a lot!
``` # from .demo_modelpart import InferenceDemo import gradio as gr import os # import time import cv2 import torch # import random import numpy as np from llava import conversation...
same question