Image-Text-to-Text
Transformers
Safetensors
lora
Inference Endpoints
takarajordan commited on
Commit
dbb98f9
1 Parent(s): 7c1495b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +16 -1
README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - lora
9
  datasets:
10
  - Multimodal-Fatima/FGVC_Aircraft_train
 
11
  ---
12
  # pixtral_aerial_VQA_adapter
13
 
@@ -37,4 +38,18 @@ datasets:
37
 
38
  - **Training method**: LoRA (Low-Rank Adaptation)
39
  - **Base model**: Ertugrul/Pixtral-12B-Captioner-Relaxed
40
- - **Training hardware**: Nebius-hosted NVIDIA H100 machine
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  - lora
9
  datasets:
10
  - Multimodal-Fatima/FGVC_Aircraft_train
11
+ - takara-ai/FloodNet_2021-Track_2_Dataset_HF
12
  ---
13
  # pixtral_aerial_VQA_adapter
14
 
 
38
 
39
  - **Training method**: LoRA (Low-Rank Adaptation)
40
  - **Base model**: Ertugrul/Pixtral-12B-Captioner-Relaxed
41
+ - **Training hardware**: Nebius-hosted NVIDIA H100 machine
42
+
43
+ ## Citation
44
+
45
+ ```bibtext
46
+ @misc{rahnemoonfar2020floodnet,
47
+ title={FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding},
48
+ author={Maryam Rahnemoonfar and Tashnim Chowdhury and Argho Sarkar and Debvrat Varshney and Masoud Yari and Robin Murphy},
49
+ year={2020},
50
+ eprint={2012.02951},
51
+ archivePrefix={arXiv},
52
+ primaryClass={cs.CV},
53
+ doi={10.48550/arXiv.2012.02951}
54
+ }
55
+ ```