InternVL

InternVL copied to clipboard

[Feature] Is there a convenient and quick method to deploy a model to Android devices?

3

### Motivation InternVL2-1b is quiet good for out task, but we want to deploy itl to Android devices？ Any framework to support it? ### Related resources _No response_ ### Additional...

cloudyuyuyu

InternVL2-40B-AWQ+lmdeploy video infer speed is very slow

16

I am using the InternVL2-40B-AWQ model and performing video inference according to the multi-images inference paradigm. Each video is sampled into 24 frames, and the prompt is as follows. My...

AmazDeng

[Feature] 希望支持vLLM和Ollama/Hope to support vLLM and Ollama

1

### Motivation [Feature] 希望支持vLLM和Ollama/Hope to support vLLM and Ollama ### Related resources _No response_ ### Additional context _No response_

shenyan-008

Question: What is the minimum size of an image that can be classified?

1

I want to use InternVL2-8B to do binary classification (e.g. yes or no) on very small images. Specifically, I am going to use the cropped bounding box patch (which is...

ChangGiMoon

【question】TypeError: InternVLChatModel.forward() missing 1 required positional argument: 'pixel_values'

1

请问如果想用模型做纯文本推理，应该怎么写呢？outputs = self.model(**inputs, output_hidden_states=True, return_dict=True)，现在这样会TypeError: InternVLChatModel.forward() missing 1 required positional argument: 'pixel_values'，如果加上pixel_values=None，会有image_flags = image_flags.squeeze(-1) AttributeError: 'NoneType' object has no attribute 'squeeze'

ererdewubudesi

[Bug] Weight key issue when using lora fine-tuning(Already fixed)

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. -...

Lillianwei-h

[Feature] Linear-Probe Image Classification for InternViT-300M

1

### Motivation from this [link](https://github.com/OpenGVLab/InternVL/tree/main/classification#-evaluation), It would be good if we have 300M version of this model too. Or even just provide the .pth version and LinearProbe model script to...

AtiChetsurakul

Add `apply_chat_template` functionality

1

Hi, I realize that there is no `apply_chat_template` implemented for InternVL, which makes it not easy to integrate it into the code base with other models having apply_chat_template defined. Are...

Liyan06

[Docs] Can't evaluate GQA testdev.

1

### 📚 The doc issue I don't think it's possible to get the structure of the dataset as depicted below in the diagram as shown in the diagram. ### Suggest...

Zzzzzzzzzzj

### 📚 The doc issue 感谢 OpenGVLab 贡献 InterrnVL 优质项目，想让更多大佬能够交流 MLLM 多模态，所以开了这个群，希望对 【MLLM多模态】 加入学习！！！  加wx: yzyykm666，备注：MLLM ，邀请你加群哈！！！ ### Suggest a potential alternative/fix _No response_

km1994