InternVL

InternVL copied to clipboard

### Checklist - [ ] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version....

ieellee

InternVL3.5-8B 幻觉有点明显

2

随便输入一张图片（XX不在图片中），然后问 “帮我找找XX在哪里放着？”，直接回复了详细的位置，太容易测出来幻觉了

Single430

Unable to reproduce performance on MMMU-val of InternVL3.5-8B model with VLMEvalKit

1

Hello, Thank you for sharing your incredible work of InternVL, including code and models. Am trying to reproduce the amazing results reported in the paper. However, am getting 48.67 performance...

sampathchanda

[Bug]

1

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

fuhongxue00

### Motivation When InternVL to support Megatron-LM finetuning, do we have plans on it? ### Related resources _No response_ ### Additional context _No response_

robotsp

Unable to reproduce the MMMU effect of think mode

1

Excellent work! When I tried to use the Vlmevalkit tool to reproduce the performance of the InternVL3.5 2B model on the MMMU, I found that the evaluation was very slow...

sjhdbsmb

Internvl3.5 fine tune脚本

4

wuzhaodongaipython

About sft efficiency for InternVL3.5

8

Hi, I was trying to sft InternVL3.5-4B with a GPU cluster 128xA100. Yet for bs=512, grad_accm=4, per steps still takes around 1 minute which is quite slow for a 4B...

NeutrinoLiu

关于Internvl3.5的训练

24

非常amazing的工作！paper里面提到是基于xtuner训练的，是否会开源相关的训练code呢？

Zxr1314

internvl3.5 lora finetune code, would you release ?

7

### 📚 The doc issue is this be avaiable ? ### Suggest a potential alternative/fix _No response_

whcjb