GRPO training datasets for open-world image classification (Oxford-IIIT Pet): direct and structured-reasoning variants. From my lmms-owc work.
Juan CM
jucamohedano
AI & ML interests
AI Systems MSc at Trento 🚀🤖
Recent Activity
published a dataset 2 days ago
jucamohedano/experts-ml-selfcond-result updated a dataset 2 days ago
jucamohedano/experts-ml-selfcond-result updated a collection 22 days ago
OVEN GRPO sweep (Qwen3-VL-4B)Organizations
models 38
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-traversal-wikidata-lora
Image-Text-to-Text • Updated • 47
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-traversal-lora
Image-Text-to-Text • Updated • 56 • 1
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-computebuffer-lora
Image-Text-to-Text • Updated • 50
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-standard-lora
Image-Text-to-Text • Updated • 53
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-rsa-lora
Image-Text-to-Text • Updated • 51
jucamohedano/qwen3-vl-4b-oven-grpo-unlockable-clean-lora
Image-Text-to-Text • Updated • 44
jucamohedano/qwen3-vl-4b-oven-grpo-traversal-wikidata-shaped
Image-Text-to-Text • Updated • 47
jucamohedano/qwen3-vl-4b-oven-grpo-traversal-wikidata-exact
Image-Text-to-Text • Updated • 47
jucamohedano/qwen3-vl-4b-oven-grpo-traversal-structured-shaped
Image-Text-to-Text • Updated • 43
jucamohedano/qwen3-vl-4b-oven-grpo-traversal-structured-exact
Image-Text-to-Text • Updated • 43
datasets 7
jucamohedano/experts-ml-selfcond-result
Updated • 20
jucamohedano/oven-grpo-training-data
Viewer • Updated • 522k • 81
jucamohedano/oven-qwen3-vl-eval-traces
Preview • Updated • 49
jucamohedano/oxford-pets-grpo-think
Viewer • Updated • 6.61k • 212
jucamohedano/oxford-pets-grpo
Viewer • Updated • 6.61k • 198
jucamohedano/Qwen3-30B-A3B-Instruct-2507_custom_60_predict
Viewer • Updated • 60 • 26
jucamohedano/Qwen3-30B-A3B-Instruct-2507_custom_60_cot
Viewer • Updated • 60 • 23