MiniGPT-4 icon indicating copy to clipboard operation
MiniGPT-4 copied to clipboard

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

Results 330 MiniGPT-4 issues
Sort by recently updated
recently updated
newest added

(Apologies for the clumsy formatting.) Hello, I am trying to run MiniGPT-4 locally on my PC (Windows 10). After installing Python 3.11.3 (64-bit) I downloaded the code for MiniGPT-4 at...

Second finetuning stage >CUDA_VISIBLE_DEVICES=2 python3 train.py --cfg-path train_configs/minigpt4_stage2_finetune.yaml error ``` Traceback (most recent call last): File "/home/ocr/projects/llm/MiniGPT-4/MiniGPT-4/train.py", line 104, in main() File "/home/ocr/projects/llm/MiniGPT-4/MiniGPT-4/train.py", line 100, in main runner.train() File "/home/ocr/projects/llm/MiniGPT-4/MiniGPT-4/minigpt4/runners/runner_base.py",...

when i run this command: `torchrun --nproc-per-node 1 --master_port 25641 train.py --cfg-path train_configs/minigpt4_stage2_finetune.yaml` this error occurs, how can i fix it? ``` ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 81571) of...

if i have like 2 16GB GPUs, how can I inference the 13B model?

Pulling new github page to MAIN.

It happened more than once or twice. I launch the demo locally, and I think it's unlikely that the upload of the image was unsuccessful. It also happens even though...

Thanks to this great work, I was able to self host the 7B version at [agireact.com](https://agireact.com) Can also access it via discord bot. [Server invite](https://discord.com/invite/SgmBydQ2Mn) Feel free to give it...

我将mini-gpt4部署到本地了,现在不需要使用web上传图片了。可批量加载图片,欢迎来玩。 项目地址:[MiniGPT-4-local] (https://github.com/cjl09/MiniGPT-4-local) "I have deployed Mini-GPT4 **locally**, and now there's no need to use web for uploading images. It can **batch load images**, and you are welcome to play...

**Describe the bug** I have download the IconQA dataset through the link, but I find the way of organization of the data is different with the required. The images and...

In [MiniGPT-4/dataset /README_MINIGPTv2_FINETUNE.md](https://github.com/Vision-CAIR/MiniGPT-4/blob/main/dataset/README_MINIGPTv2_FINETUNE.md) the image link of TextCaps seems to be the same as the image part 1 link of Visual Genome. Maybe there is a mistake?