YanweiLi commited on
Commit
3a567d4
2 Parent(s): 8afe9f5 83a606b

Merge branch 'main' of https://huggingface.co/YanweiLi/MGM-8B

Browse files
Files changed (1) hide show
  1. README.md +52 -0
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - vision-language model
4
+ - llama
5
+ - generation
6
+ datasets:
7
+ - YanweiLi/MGM-Instruction
8
+ ---
9
+
10
+ # MGM-8B Model Card
11
+ <a href='https://github.com/dvlab-research/MGM'><img src='https://img.shields.io/badge/Project-Code-violet'></a>
12
+ <a href='https://mini-gemini.github.io/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
13
+ <a href='https://arxiv.org/pdf/2403.18814.pdf'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
14
+
15
+ ## Model details
16
+ The framework supports a series of dense and MoE Large Language Models (LLMs) from 2B to 34B with HD image understanding, reasoning, and generation simultaneously.
17
+
18
+ Normal resolution setting: [MGM-2B](https://huggingface.co/YanweiLi/MGM-2B), [MGM-7B](https://huggingface.co/YanweiLi/MGM-7B), [MGM-13B](https://huggingface.co/YanweiLi/MGM-13B), [MGM-8x7B](https://huggingface.co/YanweiLi/MGM-8x7B), [MGM-34B](https://huggingface.co/YanweiLi/MGM-34B)
19
+
20
+ High resolution setting: [MGM-7B-HD](https://huggingface.co/YanweiLi/MGM-7B-HD), [MGM-8B-HD](https://huggingface.co/YanweiLi/MGM-8B-HD), [MGM-13B-HD](https://huggingface.co/YanweiLi/MGM-13B-HD), [MGM-8x7B-HD](https://huggingface.co/YanweiLi/MGM-8x7B-HD), [MGM-34B-HD](https://huggingface.co/YanweiLi/MGM-34B-HD)
21
+
22
+
23
+ **Model type:**
24
+ MGM is an open-source chatbot trained by fine-tuning LLaMA/Vicuna on GPT-generated multimodal instruction-following data.
25
+
26
+ It empowers existing frameworks to support HD image understanding, reasoning, and generation simultaneously.
27
+
28
+ **Model version:**
29
+ MGM with LLM Meta-Llama-3-8B-Instruct
30
+
31
+ **Model date:**
32
+ MGM-8B was trained on 04/2024.
33
+
34
+ ## License
35
+ Llama 3 is licensed under the LLAMA 3 Community License,
36
+ Copyright (c) Meta Platforms, Inc. All Rights Reserved.
37
+
38
+ **Where to send questions or comments about the model:**
39
+ https://github.com/dvlab-research/MGM/issues
40
+
41
+ ## Intended use
42
+ **Primary intended uses:**
43
+ The primary use is research on large multimodal models and chatbots.
44
+
45
+ **Primary intended users:**
46
+ The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.
47
+
48
+ ## Training data
49
+ This model is trained based on [MGM-Instruction](https://huggingface.co/datasets/YanweiLi/MGM-Instruction) dataset, please to the [Github](https://github.com/dvlab-research/MGM) for more detail.
50
+
51
+ ## Acknowledgement
52
+ This project is not affiliated with Google LLC.