Distilling the 13B SpaceLLaVA VLM-as-a-Judge into a Florence-2 model to efficiently quality filter spatialVQA datasets like OpenSpaces
Salma Mayorquin PRO
salma-remyx
AI & ML interests
None yet
Recent Activity
updated
a dataset
1 day ago
salma-remyx/dpo_test_startup_dataset
published
a dataset
1 day ago
salma-remyx/dpo_test_startup_dataset
updated
a dataset
2 days ago
remyxai/SpaceThinker
Organizations
Collections
2
models
42
salma-remyx/deepseekvlm-finetune-7B
Updated
salma-remyx/vlm-finetune
Updated
•
10
salma-remyx/vlm-finetune-new
Updated
salma-remyx/qwen2.5-3b-instruct-trl-sft-openspaces_3epoch_a256_r128
Updated
salma-remyx/test_train_general_1
Updated
•
1
salma-remyx/qwen2-7b-instruct-trl-sft-openspaces
Updated
salma-remyx/qwen2-7b-instruct-trl-sft-openspaces_3epoch_a256_r128
Updated
salma-remyx/SpaceJudge
Text Generation
•
Updated
•
3
•
1
salma-remyx/SpaceQwen2-VL-7B-Instruct
Image-Text-to-Text
•
Updated
•
11
salma-remyx/spaceqwen2-7b-instruct
Updated
datasets
63
salma-remyx/dpo_test_startup_dataset
Viewer
•
Updated
•
5
•
9
salma-remyx/vqasynth_processed_r1_12k
Viewer
•
Updated
•
12.7k
•
14
salma-remyx/vqasynth_processed_r1_12k_full_reasoning
Viewer
•
Updated
•
12.7k
•
12
salma-remyx/vqasynth_processed_r1_latest
Viewer
•
Updated
•
9.17k
•
20
salma-remyx/vqasynth_processed_r1_latest_full_reasoning
Viewer
•
Updated
•
9.17k
•
36
salma-remyx/vqasynth_processed_r1_latest_full
Viewer
•
Updated
•
9.17k
•
28
salma-remyx/vqasynth_processed_r1
Viewer
•
Updated
•
12.7k
•
25
salma-remyx/vqasynth_processed_r1_full
Viewer
•
Updated
•
12.7k
•
24
salma-remyx/vqasynth_sample_processed
Viewer
•
Updated
•
5
•
119
salma-remyx/vqasynth_sample_processed_full_reasoning
Viewer
•
Updated
•
5
•
25