dindang/FloorMaterialAnalyzer_AI_Model
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Upload README.md with huggingface_hub

Browse Source
This commit is contained in:
Weiyun Wang 2025-04-12 07:23:24 +00:00 committed by system
parent d10a145035
commit 89ef9a8235
No known key found for this signature in database
GPG Key ID: 6A528E38E0733467
1 changed files with 22 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
README.md
View File

@ -9,7 +9,7 @@ base_model:
- Qwen/Qwen2.5-7B - Qwen/Qwen2.5-7B
base_model_relation: merge base_model_relation: merge
datasets: datasets:
- OpenGVLab/MMPR-v1.1 - OpenGVLab/MMPR-v1.2
language: language:
- multilingual - multilingual
tags: tags:
@ -31,7 +31,7 @@ tags:
We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance. We introduce InternVL3, an advanced multimodal large language model (MLLM) series that demonstrates superior overall performance.
Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more. Compared to InternVL 2.5, InternVL3 exhibits superior multimodal perception and reasoning capabilities, while further extending its multimodal capabilities to encompass tool usage, GUI agents, industrial image analysis, 3D vision perception, and more.
Additionally, benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series, which serves as the initialization of the langauge component in InternVL3. Additionally, we compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3. Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/fMRWSzB8ysrafQ2XJW9WR.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/fMRWSzB8ysrafQ2XJW9WR.png)
@ -49,6 +49,8 @@ In the following table, we provide an overview of the InternVL3 series.
| InternVL3-38B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-38B) | | InternVL3-38B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-38B) |
| InternVL3-78B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-78B) | | InternVL3-78B | [InternViT-6B-448px-V2_5](https://huggingface.co/OpenGVLab/InternViT-6B-448px-V2_5) | [Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) | [🤗 link](https://huggingface.co/OpenGVLab/InternVL3-78B) |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/9wf54ERGoiM3-QICkj3Oc.png)
## Model Architecture ## Model Architecture
As shown in the following figure, [InternVL3](https://internvl.github.io/blog/2025-04-11-InternVL-3/) retains the same model architecture as [InternVL 2.5](https://internvl.github.io/blog/2024-12-05-InternVL-2.5/) and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector. As shown in the following figure, [InternVL3](https://internvl.github.io/blog/2025-04-11-InternVL-3/) retains the same model architecture as [InternVL 2.5](https://internvl.github.io/blog/2024-12-05-InternVL-2.5/) and its predecessors, InternVL 1.5 and 2.0, following the "ViT-MLP-LLM" paradigm. In this new version, we integrate a newly incrementally pre-trained InternViT with various pre-trained LLMs, including InternLM 3 and Qwen 2.5, using a randomly initialized MLP projector.
@ -104,35 +106,45 @@ In this work, we use the Best-of-N evaluation strategy and employ [VisualPRM-8B]
### Multimodal Reasoning and Mathematics ### Multimodal Reasoning and Mathematics
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/Vg18MtN8tpX-eF4ls6m26.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/uVIhB9BKlirAc6zlQYI0a.png)
### OCR, Chart, and Document Understanding ### OCR, Chart, and Document Understanding
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/cx3DG7RfFg5LvHfbjqyWg.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/ivWJi3Rx_snJTfq--_9kD.png)
### Multi-Image & Real-World Comprehension ### Multi-Image & Real-World Comprehension
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/po72y3ypO6_RmtXty0b0U.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/y1OnFvJxei4dd9ZzCZ6yo.png)
### Comprehensive Multimodal & Hallucination Evaluation ### Comprehensive Multimodal & Hallucination Evaluation
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/RFykBfuGY8sJ3paZpmj39.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/XeBACd5_k_1lBbT70c6rp.png)
### Visual Grounding ### Visual Grounding
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/N2V8VPGmcivyKvOAS7F5H.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/LFBrfb6amBxL_WKOqs5gr.png)
### Multimodal Multilingual Understanding ### Multimodal Multilingual Understanding
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/wPKL20-qJj4HZGuLn1bmf.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/1wc3dA3KwIeMWOVja2GF0.png)
### Video Understanding ### Video Understanding
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/NuC0HDxJyW-JmvckMAqE8.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/qU5-6VDYtFcXxSq2bNH7T.png)
### GUI Grounding
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/FRmXQGxgjbp1O_fYeJ2he.png)
### Spatial Reasoning
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/J4AmWoDuJ6JwILdtsNJcN.png)
## Evaluation on Language Capability ## Evaluation on Language Capability
Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series, which serves as the initialization of the langauge component in InternVL3. We compare InternVL3 with Qwen2.5 Chat models, whose corresponding pre-trained base models are employed as the initialization of the langauge component in InternVL3.
Benefitting from Native Multimodal Pre-Training, the InternVL3 series achieves even better overall text performance than the Qwen2.5 series.
Please note that the evaluation scores of Qwen2.5 series may differ from those officially reported, as we have adopted the prompt versions provided in the table across all datasets for OpenCompass evaluation.
![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/geqAQiiganmQiDY65VIpm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/619507e7b74b6c591f794340/geqAQiiganmQiDY65VIpm.png)