update
Browse files- .gitattributes +1 -0
- README.md +49 -0
- added_tokens.json +3 -0
- config.json +3 -0
- generation_config.json +3 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +3 -0
- preprocessor_config.json +3 -0
- processor_config.json +3 -0
- special_tokens_map.json +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +3 -0
- vocab.json +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,52 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- FreedomIntelligence/PubMedVision
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
- zh
|
8 |
+
pipeline_tag: text-generation
|
9 |
---
|
10 |
+
<div align="center">
|
11 |
+
<h1>
|
12 |
+
HuatuoGPT-Vision-7B
|
13 |
+
</h1>
|
14 |
+
</div>
|
15 |
+
|
16 |
+
<div align="center">
|
17 |
+
<a href="https://github.com/FreedomIntelligence/HuatuoGPT-Vision" target="_blank">GitHub</a> | <a href="https://arxiv.org/abs/2406.19280" target="_blank">Paper</a>
|
18 |
+
</div>
|
19 |
+
|
20 |
+
# <span id="Start">Introduction</span>
|
21 |
+
HuatuoGPT-Vision is a multimodal LLM for medical applications, built with the [PubMedVision dataset](https://huggingface.co/datasets/FreedomIntelligence/PubMedVision). HuatuoGPT-Vision-7B is trained based on Qwen2-7B using the LLaVA-v1.5 architecture.
|
22 |
+
|
23 |
+
# <span id="Start">Quick Start</span>
|
24 |
+
|
25 |
+
1. Get the model inference code from [Github](https://github.com/FreedomIntelligence/HuatuoGPT-Vision).
|
26 |
+
```bash
|
27 |
+
git clone https://github.com/FreedomIntelligence/HuatuoGPT-Vision.git
|
28 |
+
```
|
29 |
+
2. Model inference
|
30 |
+
```python
|
31 |
+
query = 'What does the picture show?'
|
32 |
+
image_paths = ['image_path1']
|
33 |
+
|
34 |
+
from cli import HuatuoChatbot
|
35 |
+
bot = HuatuoChatbot(huatuogpt_vision_model_path) # load the model
|
36 |
+
output = bot.inference(query, image_paths) # generation
|
37 |
+
print(output) # Prints the model output
|
38 |
+
```
|
39 |
+
|
40 |
+
# <span id="Start">Citation</span>
|
41 |
+
|
42 |
+
```
|
43 |
+
@misc{chen2024huatuogptvisioninjectingmedicalvisual,
|
44 |
+
title={HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scale},
|
45 |
+
author={Junying Chen and Ruyi Ouyang and Anningzhe Gao and Shunian Chen and Guiming Hardy Chen and Xidong Wang and Ruifei Zhang and Zhenyang Cai and Ke Ji and Guangjun Yu and Xiang Wan and Benyou Wang},
|
46 |
+
year={2024},
|
47 |
+
eprint={2406.19280},
|
48 |
+
archivePrefix={arXiv},
|
49 |
+
primaryClass={cs.CV},
|
50 |
+
url={https://arxiv.org/abs/2406.19280},
|
51 |
+
}
|
52 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f900417fc79218977bee7c9dc6d1174c3f790e4d52f0e6f47f3fd7ff08997d3
|
3 |
+
size 645
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74b5c5bdfdaab39a0e09bd1f9b8172790cbc3ff7e220ff875d661a1e5297e740
|
3 |
+
size 4681
|
generation_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b170f1e09c5b74a2499f05422e3f94dde8cf95b614339c9f664c5fd4022b39
|
3 |
+
size 146
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ae885297028feb0137487c2f6a1b279740f0674faafee968217b5a3c391a0a2
|
3 |
+
size 4993387384
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f99c4b11ca6fe8d92380df71f473e2d232537173908890081558c8b3b632764a
|
3 |
+
size 4991483200
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9acab7b61f119f222efa1a0b808be9beeec37b6d3110a0a7522e01d008a43031
|
3 |
+
size 4796984024
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af502d33aa7203f24a2b45c93a194882f2524ed24ec381e2d954f6f245ac3294
|
3 |
+
size 1090453648
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d8fe0c95f2820bb298cafb19e66d852e9930753ccdb73f40939b033cf5060d3
|
3 |
+
size 74650
|
preprocessor_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8d5e64ee5c07ff6d70142856d178ac39d0563da3612e32110fa824f5337b7a1
|
3 |
+
size 505
|
processor_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad6763938cfa248703771e3ff808b5d565a6a8677a8e2832583faebeae3689d7
|
3 |
+
size 134
|
special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d7c696619d62c42ab84e1caa94075037d46ba526d11dda1651eea9e586526b5
|
3 |
+
size 608
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5af1f35167ef12bba600c55d480386c944ed100b63c7329653ed1caec43bedbe
|
3 |
+
size 11422262
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9589589fbec769f31f13a6e917393922577767df389d25c6c220e00c80fadf
|
3 |
+
size 7606
|
vocab.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910
|
3 |
+
size 2776833
|