MiniCPM-V

MiniCPM-V copied to clipboard

package versions have conflicting dependencies.

1

ERROR: Cannot install -r requirements.txt (line 18) and -r requirements.txt (line 32) because these package versions have conflicting dependencies. The conflict is caused by: spacy 3.7.2 depends on typer=0.3.0 gradio...

cvmilesight

类似这种：https://github.com/ymcui/Chinese-LLaMA-Alpaca-3/wiki/openai_api_zh @iceflame89

xiaoToby

如题，想在边缘设备上使用，算力不高1.5 TOPS

shenyunhuan

Questions about resource configuration

3

Hi, if I want to achieve the same effect as Online Demo, what resource configuration should I use?

uuhc

finetune/dataset.py | TypeError: Cannot cast array data from dtype('float64') to dtype('int32') according to the rule 'same_kind'

8

Error INFO: File "/root/git_projects/MiniCPM-V/finetune/finetune.py", line 208, in train() File "/root/git_projects/MiniCPM-V/finetune/finetune.py", line 203, in train trainer.train() File "/root/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 1885, in train return inner_training_loop( File "/root/miniconda3/lib/python3.10/site-packages/transformers/trainer.py", line 2291, in _inner_training_loop self._maybe_log_save_evaluate(tr_loss,...

JamePeng

生成错误描述

3

## 问题描述 使用MiniCPM-V2进行图像描述生成任务，模型输出与图像不相关内容，并且可复现。 以下是我本地测试的环境、推理代码以及生成的描述。 ### 推理环境 下面是本地测试中部分安装包版本 ```json torch==2.3.0 torchvision==0.18.0 timm==0.9.16 transformers==4.37.2 ``` ### 推理代码及参数设置 下面是推理时设置的参数 ```python from transformers import AutoModel, AutoTokenizer model_path = "my-model-path" model = AutoModel.from_pretrained( model_path, trust_remote_code=True,...

ZHANG-SH97

多轮对话效果不佳

2


CanvaChen

您好，我下载了mlc-MiniCPM提供的MiniCPM-V 2.0的安卓demo，下载完模型后进行问答，有时会下如图所示的异常输出，请问这个主要是什么原因造成的呢？ 使用的手机型号为iqoo neo8 pro,配置为天玑9200+16g内存 

zjts

when can we get the code of train from scratch?

2

it`s a good project , But how to train from scratch?, could you give the train code and dataset? it is very important, thank you .

sankexin

I want to know the use of the gpu of MiniCPM-Llama3-V 2.5

1

I'd like to ask how much gpu memory is needed for this model inference and training

praymich