Hugging Face's logo

AIDC-AI
/
Ovis-Clip-Qwen1_5-7B

Image-Text-to-Text
Transformers
PyTorch
ovis
text-generation
MLLM
custom_code
Model card Files Community
runninglsy commited on
Commit
265e6cc
•
1 Parent(s): f5cfd8b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -10,6 +10,10 @@ tags:
10
  ## Introduction
11
  Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to [Ovis paper](https://arxiv.org/abs/2405.20797) and [Ovis GitHub](https://github.com/AIDC-AI/Ovis).
12
 
 
 
 
 
13
  ## Model
14
  Ovis can be instantiated with popular LLMs (e.g., Qwen, Llama3). We provide the following pretrained Ovis MLLMs:
15
 
 
10
  ## Introduction
11
  Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to [Ovis paper](https://arxiv.org/abs/2405.20797) and [Ovis GitHub](https://github.com/AIDC-AI/Ovis).
12
 
13
+ <div align="center">
14
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/658a8a837959448ef5500ce5/TIlymOb86R6_Mez3bpmcB.png" width="100%" />
15
+ </div>
16
+
17
  ## Model
18
  Ovis can be instantiated with popular LLMs (e.g., Qwen, Llama3). We provide the following pretrained Ovis MLLMs:
19