---
title: InternVL-14B-FlickrCN-FT-364px
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px.md"
repository: Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px
last_updated: 2024-12-30
license: mit
base_model:
  - OpenGVLab/InternVL-14B-224px
base_model_relation: finetune
library_name:
  - pytorch
  - transformer
frameworks:
  - pytorch
downloads: 1165
stars: 0
tags:
  - "Image-to-Text Retrieval"
  - "Text-To-Image Retrieval"
---

# InternVL-14B-FlickrCN-FT-364px

> InternVL-14B-FlickrCN-FT-364px - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。InternVL-14B-FlickrCN-FT-364px

Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可，基于 OpenGVLab/InternVL-14B-224px 构建。

- **Repository**: Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px
- **License**: mit
- **Base model**: OpenGVLab/InternVL-14B-224px
- **Tags**: Image-to-Text Retrieval, Text-To-Image Retrieval
- **Downloads**: 1165
- **Stars**: 0
- **Last updated**: 2024-12-30

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/InternVL-14B-FlickrCN-FT-364px

---

# InternVL-14B-FlickrCN-FT-364px

## What is InternVL?

\[[Paper](https://arxiv.org/abs/2312.14238)\]  \[[GitHub](https://github.com/OpenGVLab/InternVL)\]   \[[Chat Demo](https://internvl.opengvlab.com/)\]

InternVL scales up the ViT to _**6B parameters**_ and aligns it with LLM.

It is _**the largest open-source vision/vision-language foundation model (14B)**_ to date, achieving _**32 state-of-the-art**_ performances on a wide range of tasks such as visual perception, cross-modal retrieval, multimodal dialogue, etc.


![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/k5UATwX5W2b5KJBN5C58x.png)


## Model Details
- **Model Type:** fine-tuned retrieval model
- **Support Tasks:** image-text retrieval
- **Model Stats:**
  - Params: 14B
  - Image size: 364 x 364
- **Fine-tune Dataset:** FlickrCN

## Setting

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/yuGYJIUQmgc6o87JulBMK.png)

## Performance

See this [document](https://github.com/OpenGVLab/InternVL/tree/main/internvl_g#flickr30k) for more details about the evaluation.

![image/png](https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/6_m-UMr6tBRxuDRXWBFnj.png)


## Model Usage

**Note: the prefix `'summarize:'` and `tokenizer.pad_token_id = 0` are necessary. Their absence will lead to abnormal results.**

```python
import torch
from PIL import Image
from transformers import AutoModel, CLIPImageProcessor
from transformers import AutoTokenizer


model = AutoModel.from_pretrained(
    'OpenGVLab/InternVL-14B-FlickrCN-FT-364px',
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True).cuda().eval()

image_processor = CLIPImageProcessor.from_pretrained('OpenGVLab/InternVL-14B-FlickrCN-FT-364px')

tokenizer = AutoTokenizer.from_pretrained(
    'OpenGVLab/InternVL-14B-FlickrCN-FT-364px', use_fast=False, add_eos_token=True)
tokenizer.pad_token_id = 0  # set pad_token_id to 0

images = [
    Image.open('./examples/image1.jpg').convert('RGB'),
    Image.open('./examples/image2.jpg').convert('RGB'),
    Image.open('./examples/image3.jpg').convert('RGB')
]
prefix = 'summarize:'
texts = [
    prefix + 'a photo of a red panda',  # English
    prefix + '一张熊猫的照片',  # Chinese
    prefix + '二匹の猫の写真'  # Japanese
]

pixel_values = image_processor(images=images, return_tensors='pt').pixel_values
pixel_values = pixel_values.to(torch.bfloat16).cuda()
input_ids = tokenizer(texts, return_tensors='pt', max_length=80,
                      truncation=True, padding='max_length').input_ids.cuda()

# InternVL-C
logits_per_image, logits_per_text = model(
    image=pixel_values, text=input_ids, mode='InternVL-C')
probs = logits_per_image.softmax(dim=-1)

# InternVL-G
logits_per_image, logits_per_text = model(
    image=pixel_values, text=input_ids, mode='InternVL-G')
probs = logits_per_image.softmax(dim=-1)
```

## Citation

If you find this project useful in your research, please consider citing:

```BibTeX
@article{chen2023internvl,
  title={InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks},
  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and Li, Bin and Luo, Ping and Lu, Tong and Qiao, Yu and Dai, Jifeng},
  journal={arXiv preprint arXiv:2312.14238},
  year={2023}
}
```

## Acknowledgement

InternVL is built with reference to the code of the following projects: [OpenAI CLIP](https://github.com/openai/CLIP), [Open CLIP](https://github.com/mlfoundations/open_clip), [CLIP Benchmark](https://github.com/LAION-AI/CLIP_benchmark), [EVA](https://github.com/baaivision/EVA/tree/master), [InternImage](https://github.com/OpenGVLab/InternImage), [ViT-Adapter](https://github.com/czczup/ViT-Adapter), [MMSegmentation](https://github.com/open-mmlab/mmsegmentation), [Transformers](https://github.com/huggingface/transformers), [DINOv2](https://github.com/facebookresearch/dinov2), [BLIP-2](https://github.com/salesforce/LAVIS/tree/main/projects/blip2), [Qwen-VL](https://github.com/QwenLM/Qwen-VL/tree/master/eval_mm), and [LLaVA-1.5](https://github.com/haotian-liu/LLaVA). Thanks for their awesome work!