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 model
2 days ago
salma-remyx/nemotron-vlm
published
a model
2 days ago
salma-remyx/nemotron-vlm
new activity
3 days ago
remyxai/SpaceQwen2.5-VL-3B-Instruct:Performance
Organizations
Collections
2
models
43
salma-remyx/nemotron-vlm
Updated
salma-remyx/deepseekvlm-finetune-7B
Updated
salma-remyx/vlm-finetune
Updated
•
3
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
•
1
•
1
salma-remyx/SpaceQwen2-VL-7B-Instruct
Image-Text-to-Text
•
Updated
•
11
datasets
63
salma-remyx/dpo_test_startup_dataset
Viewer
•
Updated
•
5
•
29
salma-remyx/vqasynth_processed_r1_12k
Viewer
•
Updated
•
12.7k
•
20
salma-remyx/vqasynth_processed_r1_12k_full_reasoning
Viewer
•
Updated
•
12.7k
•
18
salma-remyx/vqasynth_processed_r1_latest
Viewer
•
Updated
•
9.17k
•
26
salma-remyx/vqasynth_processed_r1_latest_full_reasoning
Viewer
•
Updated
•
9.17k
•
42
salma-remyx/vqasynth_processed_r1_latest_full
Viewer
•
Updated
•
9.17k
•
33
salma-remyx/vqasynth_processed_r1
Viewer
•
Updated
•
12.7k
•
35
salma-remyx/vqasynth_processed_r1_full
Viewer
•
Updated
•
12.7k
•
31
salma-remyx/vqasynth_sample_processed
Viewer
•
Updated
•
5
•
85
salma-remyx/vqasynth_sample_processed_full_reasoning
Viewer
•
Updated
•
5
•
30