Total runs:
9.6K
Run Growth:
-350
Growth Rate:
-3.81%
Sponsored by
Gobii
artificialguybr / textcaps-teste2
Model's Last Updated: July 21 2026
image-to-text
Introduction of textcaps-teste2
Model Details of textcaps-teste2
GIT (GenerativeImage2Text), large-sized, fine-tuned on TextCaps, R*
R = re-trained by removing some offensive captions in cc12m dataset
GIT (short for GenerativeImage2Text) model, large-sized version, fine-tuned on TextCaps. It was introduced in the paper GIT: A Generative Image-to-text Transformer for Vision and Language by Wang et al. and first released in this repository .
Disclaimer: The team releasing GIT did not write a model card for this model so this model card has been written by the Hugging Face team.
Model description
GIT is a Transformer decoder conditioned on both CLIP image tokens and text tokens. The model is trained using "teacher forcing" on a lot of (image, text) pairs.
The goal for the model is simply to predict the next text token, giving the image tokens and previous text tokens.
The model has full access to (i.e. a bidirectional attention mask is used for) the image patch tokens, but only has access to the previous text tokens (i.e. a causal attention mask is used for the text tokens) when predicting the next text token.
This allows the model to be used for tasks like:
- image and video captioning
- visual question answering (VQA) on images and videos
- even image classification (by simply conditioning the model on the image and asking it to generate a class for it in text).
Intended uses & limitations
You can use the raw model for image captioning. See the model hub to look for fine-tuned versions on a task that interests you.
How to use
For code examples, we refer to the documentation .
Training data
From the paper:
We collect 0.8B image-text pairs for pre-training, which include COCO (Lin et al., 2014), Conceptual Captions (CC3M) (Sharma et al., 2018), SBU (Ordonez et al., 2011), Visual Genome (VG) (Krishna et al., 2016), Conceptual Captions (CC12M) (Changpinyo et al., 2021), ALT200M (Hu et al., 2021a), and an extra 0.6B data following a similar collection procedure in Hu et al. (2021a).
=> however this is for the model referred to as "GIT" in the paper, which is not open-sourced.
This checkpoint is "GIT-large", which is a smaller variant of GIT trained on 20 million image-text pairs.
Next, the model was fine-tuned on TextCaps.
See table 11 in the paper for more details.
Preprocessing
We refer to the original repo regarding details for preprocessing during training.
During validation, one resizes the shorter edge of each image, after which center cropping is performed to a fixed-size resolution. Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
Evaluation results
For evaluation results, we refer readers to the paper .
Runs of artificialguybr textcaps-teste2 on huggingface.co
9
Total runs
0
24-hour runs
1
3-day runs
-3
7-day runs
-29
30-day runs
More Information About textcaps-teste2 huggingface.co Model
Url of textcaps-teste2
textcaps-teste2 huggingface.co Url
Provider of textcaps-teste2 huggingface.co
Other API from artificialguybr
Updated:July 21 2026
Total runs:
1.7K
Run Growth:
201
Growth Rate:
11.73%
Total runs:
1.1K
Run Growth:
806
Growth Rate:
72.48%
Total runs:
898
Run Growth:
522
Growth Rate:
58.59%
Total runs:
896
Run Growth:
244
Growth Rate:
27.23%
Total runs:
527
Run Growth:
0
Growth Rate:
0.00%
Total runs:
479
Run Growth:
106
Growth Rate:
22.13%
Total runs:
458
Run Growth:
220
Growth Rate:
48.14%
Total runs:
441
Run Growth:
250
Growth Rate:
59.24%
Total runs:
414
Run Growth:
220
Growth Rate:
53.53%
Total runs:
363
Run Growth:
-72
Growth Rate:
-20.93%
Total runs:
332
Run Growth:
72
Growth Rate:
22.36%
Total runs:
298
Run Growth:
-354
Growth Rate:
-116.83%
Total runs:
284
Run Growth:
51
Growth Rate:
18.09%
Total runs:
279
Run Growth:
-16
Growth Rate:
-5.73%
Total runs:
273
Run Growth:
-82
Growth Rate:
-31.18%
Total runs:
272
Run Growth:
116
Growth Rate:
42.65%
Total runs:
257
Run Growth:
65
Growth Rate:
25.90%
Total runs:
248
Run Growth:
128
Growth Rate:
48.30%
Total runs:
240
Run Growth:
-179
Growth Rate:
-75.21%
Total runs:
227
Run Growth:
138
Growth Rate:
63.89%
Total runs:
227
Run Growth:
109
Growth Rate:
48.02%
Total runs:
219
Run Growth:
17
Growth Rate:
7.76%
Total runs:
215
Run Growth:
66
Growth Rate:
30.99%
Total runs:
205
Run Growth:
-42
Growth Rate:
-20.69%
Total runs:
196
Run Growth:
45
Growth Rate:
22.84%
Total runs:
175
Run Growth:
62
Growth Rate:
35.84%
Total runs:
173
Run Growth:
61
Growth Rate:
35.88%
Total runs:
173
Run Growth:
-146
Growth Rate:
-86.90%
Total runs:
169
Run Growth:
48
Growth Rate:
29.45%
Total runs:
166
Run Growth:
53
Growth Rate:
33.13%
Total runs:
161
Run Growth:
-62
Growth Rate:
-38.51%
Total runs:
158
Run Growth:
64
Growth Rate:
37.87%
Total runs:
158
Run Growth:
72
Growth Rate:
44.72%
Total runs:
154
Run Growth:
32
Growth Rate:
20.78%
Total runs:
137
Run Growth:
104
Growth Rate:
75.91%
Total runs:
133
Run Growth:
80
Growth Rate:
65.04%
Total runs:
127
Run Growth:
-109
Growth Rate:
-85.83%
Total runs:
114
Run Growth:
19
Growth Rate:
16.67%
Total runs:
110
Run Growth:
61
Growth Rate:
57.01%
Total runs:
108
Run Growth:
17
Growth Rate:
16.35%
Total runs:
98
Run Growth:
50
Growth Rate:
53.76%
Total runs:
95
Run Growth:
22
Growth Rate:
25.88%
Total runs:
95
Run Growth:
88
Growth Rate:
89.80%
Total runs:
95
Run Growth:
82
Growth Rate:
86.32%
Total runs:
90
Run Growth:
-17
Growth Rate:
-19.77%
Total runs:
89
Run Growth:
-1
Growth Rate:
-1.12%
Total runs:
82
Run Growth:
32
Growth Rate:
39.02%
Total runs:
80
Run Growth:
2
Growth Rate:
2.53%
Total runs:
79
Run Growth:
-35
Growth Rate:
-43.75%
Total runs:
79
Run Growth:
-26
Growth Rate:
-32.91%
Total runs:
78
Run Growth:
-93
Growth Rate:
-117.72%
Total runs:
78
Run Growth:
51
Growth Rate:
65.38%
Total runs:
75
Run Growth:
68
Growth Rate:
90.67%
Total runs:
74
Run Growth:
35
Growth Rate:
48.61%
Total runs:
72
Run Growth:
-33
Growth Rate:
-44.59%
Total runs:
72
Run Growth:
7
Growth Rate:
9.72%
Total runs:
71
Run Growth:
3
Growth Rate:
4.05%
Total runs:
69
Run Growth:
4
Growth Rate:
5.71%
Total runs:
64
Run Growth:
22
Growth Rate:
34.92%
Total runs:
63
Run Growth:
-12
Growth Rate:
-19.05%
Total runs:
63
Run Growth:
-32
Growth Rate:
-48.48%
Total runs:
61
Run Growth:
2
Growth Rate:
3.28%
Total runs:
60
Run Growth:
4
Growth Rate:
6.67%
Total runs:
60
Run Growth:
7
Growth Rate:
11.67%
Total runs:
55
Run Growth:
2
Growth Rate:
3.77%
Total runs:
55
Run Growth:
-2
Growth Rate:
-3.51%
Total runs:
54
Run Growth:
6
Growth Rate:
11.11%
Total runs:
51
Run Growth:
42
Growth Rate:
82.35%
Total runs:
50
Run Growth:
7
Growth Rate:
14.00%
Total runs:
48
Run Growth:
5
Growth Rate:
10.42%
Total runs:
48
Run Growth:
32
Growth Rate:
66.67%
Total runs:
47
Run Growth:
0
Growth Rate:
0.00%
Total runs:
45
Run Growth:
10
Growth Rate:
23.81%
Total runs:
45
Run Growth:
15
Growth Rate:
39.47%
Total runs:
41
Run Growth:
12
Growth Rate:
29.27%
Total runs:
40
Run Growth:
11
Growth Rate:
27.50%
Total runs:
39
Run Growth:
-9
Growth Rate:
-23.08%
Total runs:
39
Run Growth:
-22
Growth Rate:
-56.41%
Total runs:
39
Run Growth:
15
Growth Rate:
38.46%
Total runs:
39
Run Growth:
15
Growth Rate:
42.86%
Total runs:
37
Run Growth:
-79
Growth Rate:
-213.51%
Total runs:
35
Run Growth:
32
Growth Rate:
91.43%
Total runs:
34
Run Growth:
22
Growth Rate:
68.75%
Total runs:
34
Run Growth:
10
Growth Rate:
29.41%
Total runs:
34
Run Growth:
0
Growth Rate:
0.00%
Total runs:
32
Run Growth:
9
Growth Rate:
28.13%
Total runs:
31
Run Growth:
-14
Growth Rate:
-46.67%
Total runs:
31
Run Growth:
-30
Growth Rate:
-96.77%
Total runs:
31
Run Growth:
-28
Growth Rate:
-93.33%
Total runs:
30
Run Growth:
-26
Growth Rate:
-83.87%
Total runs:
30
Run Growth:
-8
Growth Rate:
-28.57%
Total runs:
30
Run Growth:
-24
Growth Rate:
-96.00%
Total runs:
30
Run Growth:
12
Growth Rate:
40.00%
Total runs:
30
Run Growth:
-2
Growth Rate:
-7.14%
Total runs:
30
Run Growth:
15
Growth Rate:
50.00%
Total runs:
30
Run Growth:
5
Growth Rate:
18.52%
Total runs:
29
Run Growth:
-10
Growth Rate:
-37.04%
Total runs:
29
Run Growth:
-4
Growth Rate:
-13.79%