czczup commited on
Commit
bbbad2d
β€’
1 Parent(s): a4f7638

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -12
README.md CHANGED
@@ -10,7 +10,7 @@ datasets:
10
  pipeline_tag: image-feature-extraction
11
  ---
12
 
13
- # Model Card for InternViT-6B-224px
14
 
15
  <p align="center">
16
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/jSJ7TChEGvGP_gwNhrYoA.webp" alt="Image Description" width="300" height="300">
@@ -20,15 +20,6 @@ pipeline_tag: image-feature-extraction
20
 
21
  [\[πŸ€— HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[πŸš€ Quick Start\]](#model-usage) [\[🌐 Community-hosted API\]](https://rapidapi.com/adushar1320/api/internvl-chat) [\[πŸ“– 中文解读\]](https://zhuanlan.zhihu.com/p/675877376)
22
 
23
- | Model | Date | Download | Note |
24
- | ----------------------- | ---------- | ---------------------------------------------------------------------- | -------------------------------- |
25
- | InternViT-6B-448px-V1-5 | 2024.04.20 | πŸ€— [HF link](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-5) | support dynamic resolution, super strong OCR (πŸ”₯new) |
26
- | InternViT-6B-448px-V1-2 | 2024.02.11 | πŸ€— [HF link](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-2) | 448 resolution |
27
- | InternViT-6B-448px-V1-0 | 2024.01.30 | πŸ€— [HF link](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V1-0) | 448 resolution |
28
- | InternViT-6B-224px | 2023.12.22 | πŸ€— [HF link](https://huggingface.co/OpenGVLab/InternViT-6B-224px) | vision foundation model |
29
- | InternVL-14B-224px | 2023.12.22 | πŸ€— [HF link](https://huggingface.co/OpenGVLab/InternVL-14B-224px) | vision-language foundation model |
30
-
31
-
32
  ## Model Details
33
  - **Model Type:** vision foundation model, feature backbone
34
  - **Model Stats:**
@@ -37,7 +28,6 @@ pipeline_tag: image-feature-extraction
37
  - **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
38
  - **Note:** This model has 48 blocks, and we found that using the output after the fourth-to-last block worked best for VLLM. Therefore, when building a VLLM with this model, **please use the features from the fourth-to-last layer.**
39
 
40
-
41
  ## Linear Probing Performance
42
 
43
  See this [document](https://github.com/OpenGVLab/InternVL/tree/main/classification#-evaluation) for more details about the linear probing evaluation.
@@ -88,7 +78,6 @@ If you find this project useful in your research, please consider citing:
88
  }
89
  ```
90
 
91
-
92
  ## Acknowledgement
93
 
94
  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!
 
10
  pipeline_tag: image-feature-extraction
11
  ---
12
 
13
+ # InternViT-6B-224px
14
 
15
  <p align="center">
16
  <img src="https://cdn-uploads.huggingface.co/production/uploads/64119264f0f81eb569e0d569/jSJ7TChEGvGP_gwNhrYoA.webp" alt="Image Description" width="300" height="300">
 
20
 
21
  [\[πŸ€— HF Demo\]](https://huggingface.co/spaces/OpenGVLab/InternVL) [\[πŸš€ Quick Start\]](#model-usage) [\[🌐 Community-hosted API\]](https://rapidapi.com/adushar1320/api/internvl-chat) [\[πŸ“– 中文解读\]](https://zhuanlan.zhihu.com/p/675877376)
22
 
 
 
 
 
 
 
 
 
 
23
  ## Model Details
24
  - **Model Type:** vision foundation model, feature backbone
25
  - **Model Stats:**
 
28
  - **Pretrain Dataset:** LAION-en, LAION-COCO, COYO, CC12M, CC3M, SBU, Wukong, LAION-multi
29
  - **Note:** This model has 48 blocks, and we found that using the output after the fourth-to-last block worked best for VLLM. Therefore, when building a VLLM with this model, **please use the features from the fourth-to-last layer.**
30
 
 
31
  ## Linear Probing Performance
32
 
33
  See this [document](https://github.com/OpenGVLab/InternVL/tree/main/classification#-evaluation) for more details about the linear probing evaluation.
 
78
  }
79
  ```
80
 
 
81
  ## Acknowledgement
82
 
83
  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!