Distilling the 13B SpaceLLaVA VLM-as-a-Judge into a Florence-2 model to efficiently quality filter spatialVQA datasets like OpenSpaces
Salma Mayorquin
salma-remyx
AI & ML interests
None yet
Organizations
Collections
2
models
35
salma-remyx/SpaceQwen2-VL-7B-Instruct
Image-Text-to-Text
•
Updated
•
6
salma-remyx/spaceqwen2-7b-instruct
Updated
salma-remyx/SpaceJudge
Text Generation
•
Updated
•
23
•
1
salma-remyx/hf-hub-test
Updated
salma-remyx/mistral-7b-localmentor-top1k-neft
Updated
•
10
salma-remyx/codellama-7b-instruct-ffmperative-top1k-neft
Updated
•
35
•
1
salma-remyx/aerial-view-field-sdxl-lora
Text-to-Image
•
Updated
•
40
•
•
2
salma-remyx/brain-wojak-sdxl-lora
Text-to-Image
•
Updated
•
59
•
•
2
salma-remyx/myx-sdxl-lora
Text-to-Image
•
Updated
•
30
•
•
2
salma-remyx/amumu-sdxl-lora
Text-to-Image
•
Updated
•
61
•
•
3
datasets
28
salma-remyx/vqasynth_sample_large_img
Viewer
•
Updated
•
1
•
11
salma-remyx/vqasynth_cauldron_localized_narratives_100
Viewer
•
Updated
•
41
•
42
salma-remyx/vqasynth_cauldron_localized_narratives_100_full
Viewer
•
Updated
•
41
•
36
salma-remyx/OpenSpaces-qwen-vlm-instruct
Viewer
•
Updated
•
44.1k
•
35
salma-remyx/SpaceJudgeDataset
Viewer
•
Updated
•
3.88k
•
23
•
1
salma-remyx/vqasynth_cauldron_localized_narratives_100_qwen_instruct
Viewer
•
Updated
•
205
•
42
salma-remyx/vqasynth_cauldron_localized_narratives_30K
Viewer
•
Updated
•
11.9k
•
19
salma-remyx/vqasynth_cauldron_localized_narratives_30K_full
Viewer
•
Updated
•
11.9k
•
108
salma-remyx/vqasynth_cauldron_localized_narratives_5K
Viewer
•
Updated
•
2.01k
•
39
salma-remyx/vqasynth_cauldron_localized_narratives_5K_full
Viewer
•
Updated
•
2.01k
•
37