Visual Question Answering
Transformers
Safetensors
llava
image-text-to-text
AIGC
LLaVA
Inference Endpoints
ponytail commited on
Commit
9fa9b43
·
verified ·
1 Parent(s): bee6755

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -31
README.md CHANGED
@@ -6,11 +6,14 @@ tags:
6
  - AIGC
7
  - LlaVA
8
  ---
9
- # Human-LLaVA-(HumanCaption-10M dataset)
10
 
11
  ## DEMO
12
 
13
- <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/tyT9FvycyyVWISd1-_A-m.mp4"></video>
 
 
 
14
 
15
  ### Introduction
16
 
@@ -57,46 +60,25 @@ predict = processor.decode(output[0][:], skip_special_tokens=True)
57
  print(predict)
58
  ```
59
  ## Get the Dataset
60
-
 
61
  #### Domain Alignment Stage
62
-
63
  HumanCaption-10M(self construct): Coming Soon!
64
 
65
  #### Instruction Tuning Stage
66
 
67
- #### Instruct Data Example
68
-
69
-
70
-
71
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/vRojQxm8IMybBV0X5CKbf.png)
72
-
73
- **Caption**
74
-
75
- HumanCaption-300K(self construct): Coming Soon!
76
-
77
- ShareGPT4V:
78
-
79
- **VQA**
80
-
81
  LLaVA-Instruct_zh :
82
-
83
- ShareGPT4V:
84
-
85
- **Visual Grounding**
86
-
87
  verified_ref3rec:
88
-
89
  verified_ref3reg:
90
-
91
  verified_shikra:
92
-
93
- **Face Attributes Recognition**
94
-
95
  celeba_attribute(self construct):
96
 
97
- Face_hq(self construct):
98
-
99
-
100
  ## Citation
101
 
102
  ```
 
6
  - AIGC
7
  - LlaVA
8
  ---
9
+ # Human-LLaVA
10
 
11
  ## DEMO
12
 
13
+
14
+ <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/TpN2t19Poe5YbHHP8uN7_.mp4"></video>
15
+
16
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/ur3sls4faPNlOMZ6sA_qK.png)
17
 
18
  ### Introduction
19
 
 
60
  print(predict)
61
  ```
62
  ## Get the Dataset
63
+ #### Dataset Example
64
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64259db7d3e6fdf87e4792d0/vRojQxm8IMybBV0X5CKbf.png)
65
  #### Domain Alignment Stage
 
66
  HumanCaption-10M(self construct): Coming Soon!
67
 
68
  #### Instruction Tuning Stage
69
 
70
+ HumanCaptionHQ-300K(self construct): Coming Soon!
71
+ Face_hq(self construct):Coming Soon!
72
+ humanvg_high_reg(self construct):Coming Soon!
73
+ humanvg_high_rec(self construct):Coming Soon!
74
+ ShareGPT4V_caption:
 
 
 
 
 
 
 
 
 
75
  LLaVA-Instruct_zh :
76
+ ShareGPT4V_vqa:
 
 
 
 
77
  verified_ref3rec:
 
78
  verified_ref3reg:
 
79
  verified_shikra:
 
 
 
80
  celeba_attribute(self construct):
81
 
 
 
 
82
  ## Citation
83
 
84
  ```